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. 4-GEMMASCOPE-RES-16K
    6. 10910
    Prev
    Next
    INDEX
    Explanations

    objects and purposes associated with inventions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 4-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_4/width_16k/average_l0_124
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.hook_resid_post
    Hook Layer
    4
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Efq
    -0.74
     상세
    -0.70
     totalCount
    -0.66
    Rohy
    -0.63
    OkHttpClient
    -0.61
     Houſe
    -0.60
     Theſe
    -0.60
     Cæsar
    -0.60
     getEmail
    -0.60
     Monfieur
    -0.59
    POSITIVE LOGITS
    PerformLayout
    0.62
    setVerticalGroup
    0.53
    склю
    0.46
     présentes
    0.44
     صوتيه
    0.44
     pertanto
    0.43
    InjectAttribute
    0.43
     futuras
    0.42
     generaciones
    0.42
    UnsafeEnabled
    0.42
    Activations Density 2.716%

    No Known Activations