© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 22-GEMMASCOPE-RES-16K
    11. 14720
    Prev
    Next
    INDEX
    Explanations

    technical terms and programming constructs related to software metadata and compliance

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 22-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_22/width_16k/average_l0_123
    Prompts (Dashboard)
    24,576 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
     shots
    -0.37
     shot
    -0.36
    lan
    -0.35
    ↵↵
    -0.34
    _
    -0.32
    ,
    -0.31
     (
    -0.31
    <eos>
    -0.31
    html
    -0.30
     called
    -0.30
    POSITIVE LOGITS
     CreateTagHelper
    10.50
    AddTagHelper
    2.00
     autorytatywna
    1.91
    RenderAtEndOf
    1.60
     nahilalakip
    1.52
    tagHelperRunner
    1.51
    ValueStyle
    1.48
    GOTREF
    1.41
     disambiguazione
    1.37
    Personendaten
    1.37
    Activations Density 0.000%

    No Known Activations