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. 5-GEMMASCOPE-RES-16K
    6. 4480
    Prev
    Next
    INDEX
    Explanations

    phrases that involve possessive and definitive pronouns

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.5.hook_resid_post
    Hook Layer
    5
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    baro
    -0.57
     Wes
    -0.54
     Benth
    -0.52
     dấu
    -0.52
    nó
    -0.51
    Wes
    -0.50
    Kraj
    -0.50
    ombat
    -0.50
    valho
    -0.50
    IZABETH
    -0.49
    POSITIVE LOGITS
     gotten
    1.11
     gets
    1.08
    Gets
    1.07
     Gets
    1.04
     GETS
    0.98
     got
    0.92
     get
    0.92
    gets
    0.87
     Få
    0.84
     Get
    0.82
    Activations Density 0.068%

    No Known Activations