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. 8-GEMMASCOPE-RES-16K
    6. 8759
    Prev
    Next
    INDEX
    Explanations

    personal pronouns and their references in relation to identity and desire

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 8-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_8/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.8.hook_resid_post
    Hook Layer
    8
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    FieldDescriptor
    -0.69
    SequentialGroup
    -0.65
    nosaurus
    -0.63
     Paglinawan
    -0.63
     AssemblyCulture
    -0.62
    PhysRev
    -0.62
     ffilmiau
    -0.60
    ArrowToggle
    -0.58
     '{@
    -0.58
     Roskov
    -0.57
    POSITIVE LOGITS
     him
    0.64
    isNameExpr
    0.55
     his
    0.55
    ׂ
    0.49
    让他
    0.44
    abestanden
    0.43
    териалы
    0.41
    ביוגרפיה
    0.41
    AnchorStyles
    0.41
    handelt
    0.41
    Activations Density 0.217%

    No Known Activations