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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 5022
    Prev
    Next
    INDEX
    Explanations

    conversational markers or indicators of dialogue

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

    Code snippets and special characters

    np_acts-logits-general · gemini-2.0-flash

    conjunctions followed by new clauses

    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
     expected
    -0.43
    THON
    -0.42
    ...
    -0.41
     getArguments
    -0.40
    сс
    -0.39
    és
    -0.39
    를
    -0.38
    orElseThrow
    -0.37
    дак
    -0.37
    <sup>
    -0.36
    POSITIVE LOGITS
    Hozzáférés
    0.90
     Efq
    0.88
    InitVars
    0.87
     архивлан
    0.86
    ^(@)
    0.85
    =$?
    0.84
     reset
    0.83
    )");
    0.79
    ."));
    0.76
    PerformLayout
    0.76
    Activations Density 0.103%

    No Known Activations