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. 21-GEMMASCOPE-RES-16K
    6. 6460
    Prev
    Next
    INDEX
    Explanations

    pronouns and personal references indicating relationships or actions taken by individuals

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 21-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_21/width_16k/average_l0_70
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.hook_resid_post
    Hook Layer
    21
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     виправивши
    -0.76
    ंदीखरीदारी
    -0.68
    yntaxException
    -0.63
     PublicKey
    -0.61
    __":
    -0.56
    AsUp
    -0.55
    hasData
    -0.54
    المكان
    -0.53
     Exacts
    -0.52
    onatos
    -0.52
    POSITIVE LOGITS
     call
    2.93
     calls
    2.58
    call
    2.49
     Call
    2.44
    Call
    2.42
     calling
    2.37
     CALL
    2.32
     called
    2.21
     Calls
    2.20
    calls
    2.13
    Activations Density 0.469%

    No Known Activations