© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 18-GEMMASCOPE-RES-16K
    6. 6509
    Prev
    Next
    INDEX
    Explanations

    code-related structure or commands within text

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

    Code, filenames, and paths

    np_acts-logits-general · gemini-2.0-flash

    function parameter names

    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
    ";
    -0.49
    ';
    -0.47
    ;
    -0.47
    .*;
    -0.45
    .(
    -0.44
     
    -0.43
     "";
    -0.43
    ();
    -0.42
    ”;
    -0.42
    '';
    -0.41
    POSITIVE LOGITS
    BeginContext
    0.99
    Geplaatst
    0.97
    AddTagHelper
    0.96
     дописавши
    0.95
    DoubleQuotes
    0.94
     myſelf
    0.90
     Normdatei
    0.89
    AnimationsModule
    0.89
    Personendaten
    0.88
     Majefty
    0.86
    Activations Density 0.169%

    No Known Activations