© 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. 6-GEMMASCOPE-RES-16K
    11. 5881
    Prev
    Next
    INDEX
    Explanations

    specific technical terms related to programming and data structures

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

    technical terms and identifiers related to databases, code, and software development (like Feed_ID, Quiz, SQL table definitions).

    oai_token-act-pair · claude-3-5-haiku-20241022Triggered by @neilrathi
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 6-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_6/width_16k/average_l0_70
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.6.hook_resid_post
    Hook Layer
    6
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    aarrggbb
    -1.15
    etheless
    -1.02
    principalTable
    -0.99
    Autoritní
    -0.97
     חיצוניים
    -0.97
    MigrationBuilder
    -0.95
     resourceCulture
    -0.92
     propOrder
    -0.91
    kháu
    -0.88
    GEBURTSDATUM
    -0.88
    POSITIVE LOGITS
     myſelf
    0.84
    ſelf
    0.82
    ſelves
    0.78
     Houſe
    0.76
    neſs
    0.75
     Monfieur
    0.74
     Jefus
    0.73
     Majefty
    0.72
    OfThe
    0.71
     amanda
    0.71
    Activations Density 7.372%

    No Known Activations