Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 13-GEMMASCOPE-RES-16K
    6. 9459
    Prev
    Next
    INDEX
    Explanations

    phrases that reflect personal expectations or societal pressures

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    personal pronouns and first-person statements about personal experiences and feelings.

    oai_token-act-pair · claude-3-5-haiku-20241022Triggered by @gsarti

    the beginnings of quotes or statements, particularly those starting with personal pronouns like "I" or "It".

    oai_token-act-pair · claude-3-5-sonnet-20240620Triggered by @gsarti

    The neuron identifies the beginning of quotations, especially when introduced by quotation marks, bullet points, or markers like ">" before direct speech.

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @gsarti
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 13-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_13/width_16k/average_l0_84
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.13.hook_resid_post
    Hook Layer
    13
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     houſe
    -1.08
    ^(@)
    -0.95
     myſelf
    -0.93
     purpoſe
    -0.91
     ſtate
    -0.90
     ſever
    -0.90
     المعيارى
    -0.90
     itſelf
    -0.90
    ſelves
    -0.87
    ########.
    -0.87
    POSITIVE LOGITS
     I
    0.73
    ↵↵
    0.64
    I
    0.63
     ...
    0.59
     A
    0.59
    A
    0.58
      
    0.58
    ↵
    0.57
     &
    0.57
    The
    0.55
    Activations Density 0.317%

    No Known Activations