© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 20-GEMMASCOPE-RES-16K
    11. 11963
    Prev
    Next
    INDEX
    Explanations

    syntax structures and control flow elements in programming code

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

    "+" signs

    np_acts-logits-general · gemini-2.0-flash

    `alias` followed by identifiers

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    出版年
    -0.70
    NameInMap
    -0.66
     مشارکت‌کنندگان
    -0.63
     мәкалә
    -0.59
     Normdatei
    -0.59
     هيا
    -0.58
     "";
    -0.57
     Geraadpleegd
    -0.54
     "");
    -0.54
    /**
    -0.54
    POSITIVE LOGITS
    ↵
    1.27
    ↵↵
    0.76
    </h3>
    0.70
    ↵↵↵
    0.66
    0.59
     ftill
    0.58
    </h2>
    0.56
    literals
    0.55
    LookAnd
    0.55
    ↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵
    0.54
    Activations Density 0.079%
    No Known Activations