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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 1-GEMMASCOPE-RES-16K
    6. 9643
    Prev
    Next
    INDEX
    Explanations

    the use of personal pronouns indicating the speaker's perspective

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 1-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_1/width_16k/average_l0_102
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.1.hook_resid_post
    Hook Layer
    1
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     ſeveral
    -1.06
     ―――――
    -1.04
     Theſe
    -1.03
     itſelf
    -0.98
     greateſt
    -0.98
     Houſe
    -0.95
     whoſe
    -0.94
     leſs
    -0.94
     faſt
    -0.94
     diſt
    -0.94
    POSITIVE LOGITS
     me
    4.45
     Me
    2.86
    Me
    2.53
     ME
    2.15
     us
    2.13
    me
    2.05
     him
    1.64
     меня
    1.64
     мне
    1.63
     мной
    1.60
    Activations Density 0.042%

    No Known Activations