© 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. 18-GEMMASCOPE-RES-16K
    11. 14824
    Prev
    Next
    INDEX
    Explanations

    variable assignments and return statements in code snippets

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

    Code assignments using equals signs

    np_acts-logits-general · gemini-2.0-flash

    common programming identifiers and syntax

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.hook_resid_post
    Hook Layer
    18
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    )
    -0.56
    -0.52
     pstmt
    -0.50
    an
    -0.49
    ,
    -0.47
    ers
    -0.46
    ("")

    -0.42
    benzo
    -0.42
     bearing
    -0.41
    ’
    -0.40
    POSITIVE LOGITS
     CreateTagHelper
    1.20
     "";
    1.15
    [];
    1.14
    __;
    1.02
     [];
    1.00
    ;\\
    0.99
    '';
    0.97
     {};
    0.96
    ；
    0.96
    ?;
    0.96
    Activations Density 0.207%
    No Known Activations