Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsBlogSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 131k
    5. 20-GEMMASCOPE-RES-131K
    6. 4849
    Prev
    Next
    INDEX
    Explanations

    constructs related to legislative or parliamentary processes

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

    Document section breaks where content transitions from one section to another, often between the end of one section and the beginning of a new section, heading, or content type.

    eleuther_acts_top20 · claude-3-7-sonnet-20250219Triggered by @lu-christina
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-9b-pt-res/layer_20/width_131k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    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
    évaluateur
    -0.78
     EconPapers
    -0.76
     صوتيه
    -0.69
    ConstraintMaker
    -0.66
     FetchType
    -0.65
    ########.
    -0.65
    Vidite
    -0.65
    elemField
    -0.64
     Signalez
    -0.64
    CrossRef
    -0.63
    POSITIVE LOGITS
    ">//
    0.37
     InputDecoration
    0.34
    AndroidJUnit
    0.34
    Là
    0.32
    ↵↵
    0.30
     doigt
    0.29
     いい
    0.28
     rek
    0.28
     Hat
    0.28
    Melon
    0.28
    Activations Density 0.209%

    No Known Activations