© 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-2-2B
    7. Residual Stream - 16k
    9. 22-GEMMASCOPE-RES-16K
    11. 5767
    Prev
    Next
    INDEX
    Explanations

    code structure and methods related to setting and getting attributes

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

    Java or PHP code keywords

    np_acts-logits-general · gemini-2.0-flash

    java class declarations and comments

    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
    енча
    -0.63
     تضيفلها
    -0.58
    országban
    -0.57
     =>
    -0.56
    <_>
    -0.53
    DialogTitle
    -0.53
    smarty
    -0.52
    SPATH
    -0.52
     raison
    -0.51
    eroon
    -0.51
    POSITIVE LOGITS
    public
    1.39
     public
    0.93
    /**
    0.85
    expandindo
    0.83
    @
    0.82
    Personensuche
    0.80
    private
    0.79
    CELLANEOUS
    0.67
     Audiodateien
    0.64
    protected
    0.62
    Activations Density 0.051%

    No Known Activations