© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 22-GEMMASCOPE-RES-16K
    6. 11369
    Prev
    Next
    INDEX
    Explanations

    technical terms related to document and file manipulation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    File formats or file extensions

    np_acts-logits-general · gemini-2.0-flash

    file types and formats

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 22-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_22/width_16k/average_l0_72
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.hook_resid_post
    Hook Layer
    22
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     CreateTagHelper
    -0.81
    ArgsConstructor
    -0.72
    FieldBuilder
    -0.64
     Савезне
    -0.64
     pageContext
    -0.62
     useAppContext
    -0.61
     autorytatywna
    -0.59
    ScopeManager
    -0.59
    pushFollow
    -0.59
    IsMutable
    -0.59
    POSITIVE LOGITS
     files
    1.64
     file
    1.56
     archivo
    1.17
     Files
    1.16
     fichier
    1.15
     fichiers
    1.15
    文件
    1.15
     *.
    1.13
     (.
    1.13
     FILES
    1.08
    Activations Density 0.670%

    No Known Activations