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. 15-GEMMASCOPE-RES-16K
    6. 2147
    Prev
    Next
    INDEX
    Explanations

    sections of the document that are unrelated to content or context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 15-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_15/width_16k/average_l0_78
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.15.hook_resid_post
    Hook Layer
    15
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    fromnode
    -0.62
    ivasan
    -0.53
    strtolower
    -0.49
    moso
    -0.47
    setVerticalGroup
    -0.47
    nyataan
    -0.47
    estanden
    -0.47
    kháu
    -0.46
    ordat
    -0.46
     asupra
    -0.45
    POSITIVE LOGITS
    ScopeManager
    0.79
    tagHelperRunner
    0.74
    ValueStyle
    0.64
    RTGC
    0.60
    addContainerGap
    0.58
    WithFormat
    0.58
    BASEPATH
    0.55
    odyne
    0.54
    \{\\
    0.54
    ppins
    0.52
    Activations Density 0.091%

    No Known Activations