© 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. 1781
    Prev
    Next
    INDEX
    Explanations

    function definitions and code structure within programming language syntax

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

    Lines related to msgid and translation

    np_acts-logits-general · gemini-2.0-flash

    msgid localization strings

    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
    </em>
    -0.82
    <eos>
    -0.67
    География
    -0.56
    Donc
    -0.53
     мәкалә
    -0.53
    Открыть
    -0.52
    خواندن
    -0.49
    maal
    -0.47
    anas
    -0.46
    LikeLike
    -0.46
    POSITIVE LOGITS
    <?
    0.85
    ">//
    0.85
     Roskov
    0.78
    AnchorStyles
    0.76
    LookAnd
    0.76
     الحره
    0.75
    SequentialGroup
    0.72
    __":
    0.70
     externi
    0.70
    SuppressMessage
    0.69
    Activations Density 0.169%

    No Known Activations