© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 24-GEMMASCOPE-RES-16K
    6. 3888
    Prev
    Next
    INDEX
    Explanations

    code-related constructs and operations, particularly in programming languages

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

    Code-related keywords and classnames

    np_acts-logits-general · gemini-2.0-flash

    path delimiters and trailing punctuation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 24-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_24/width_16k/average_l0_73
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.hook_resid_post
    Hook Layer
    24
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    "});
    -1.43
    ]");
    -1.36
    '});
    -1.35
    )");
    -1.34
    ')):
    -1.32
     }}$}
    -1.30
    >');
    -1.29
    ()]);
    -1.28
    )))));
    -1.27
    ."));
    -1.27
    POSITIVE LOGITS
    ↵↵
    0.90
    glGen
    0.50
    newtheorem
    0.47
    íritu
    0.45
    strahlung
    0.44
    μως
    0.42
    instancetype
    0.41
     cwt
    0.40
     correr
    0.39
     priced
    0.39
    Activations Density 0.084%

    No Known Activations