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. 6-GEMMASCOPE-RES-16K
    6. 206
    Prev
    Next
    INDEX
    Explanations

    the presence of class initializers and related methods in code

    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
    цезда
    -0.46
    End
    -0.45
    $_['
    -0.43
    Naive
    -0.42
     board
    -0.42
    abes
    -0.42
     seleccione
    -0.41
    aturen
    -0.41
    ENDO
    -0.41
    ngo
    -0.41
    POSITIVE LOGITS
    init
    1.25
    脚注の使い方
    1.04
    RetentionPolicy
    0.95
    </thead>
    0.90
    viewDidLoad
    0.89
     BoxDecoration
    0.89
     init
    0.87
     שוליים
    0.82
    ConstraintMaker
    0.82
    참고
    0.82
    Activations Density 0.021%

    No Known Activations