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

    Neuronpedia

    APIAssistant AxisNEWCircuit 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. 6-GEMMASCOPE-RES-16K
    6. 12241
    Prev
    Next
    INDEX
    Explanations

    instances of the verb "to be" in various forms and their contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 6-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_6/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.6.hook_resid_post
    Hook Layer
    6
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     shouldn
    -0.65
     couldn
    -0.63
     isn
    -0.61
     doesn
    -0.60
     wasn
    -0.60
     weren
    -0.59
     wouldn
    -0.58
     extra
    -0.58
     hasn
    -0.58
     didn
    -0.57
    POSITIVE LOGITS
    aarrggbb
    0.92
    WEBPACK
    0.86
    AutoScaleMode
    0.85
    mektedir
    0.81
    complexContent
    0.77
    ніципалі
    0.76
     utafitiHapana
    0.76
    maktadır
    0.73
    extAlignment
    0.71
     destes
    0.69
    Activations Density 0.893%

    No Known Activations