© 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. 15-GEMMASCOPE-RES-16K
    11. 1971
    Prev
    Next
    INDEX
    Explanations

    reported speech or quotations

    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
     AssemblyCulture
    -1.04
     صوتيه
    -0.97
    hoeddwyd
    -0.88
     <>",
    -0.87
     dAtA
    -0.83
     transfieras
    -0.82
    AddTagHelper
    -0.82
     mapStateToProps
    -0.81
     Efq
    -0.81
     ComVisible
    -0.80
    POSITIVE LOGITS
    .
    0.48
    ↵↵
    0.47
     Wellen
    0.43
     noting
    0.43
     őket
    0.43
    すす
    0.42
    ,
    0.41
     recalling
    0.40
    </blockquote>
    0.40
     admits
    0.40
    Activations Density 0.042%

    No Known Activations