© 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. 18-GEMMASCOPE-RES-16K
    11. 8899
    Prev
    Next
    INDEX
    Explanations

    technical terms and structured data related to programming and software development

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

    Code snippets and file-related terms

    np_acts-logits-general · gemini-2.0-flash

    programming identifiers and types

    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
     <<<<<<<<<<<<<<
    -0.46
    cially
    -0.45
    ↵
    -0.44
     addirittura
    -0.43
     وقال
    -0.43
    .
    -0.42
     Taktlose
    -0.41
     المعرف
    -0.41
    cookieParser
    -0.40
    ↵↵
    -0.40
    POSITIVE LOGITS
     ModelExpression
    0.73
    хьтан
    0.70
     Baillargeon
    0.68
     specchio
    0.67
     Référence
    0.62
    ]--;
    0.62
     насељу
    0.62
     <=",
    0.61
     виправивши
    0.60
    PDOException
    0.58
    Activations Density 0.381%

    No Known Activations