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. 8788
    Prev
    Next
    INDEX
    Explanations

    boolean values and their assignments in programming code

    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
    Посилання
    -0.69
     bislang
    -0.61
    __*/
    -0.61
    WireFormatLite
    -0.59
     linkovi
    -0.57
    UTIVE
    -0.55
    onAttach
    -0.55
     المعيارى
    -0.55
    ichia
    -0.54
    OCCURRED
    -0.53
    POSITIVE LOGITS
    dflare
    0.58
    PerformLayout
    0.58
    ValueStyle
    0.57
    forName
    0.56
    ContentAlignment
    0.55
    BeginContext
    0.54
    setVerticalGroup
    0.54
     HasFactory
    0.54
    RetentionPolicy
    0.53
     Tats
    0.50
    Activations Density 0.064%

    No Known Activations