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. 114932
    Prev
    Next
    INDEX
    Explanations

    attributes related to small mechanical objects and their functions

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

    Adjective modifiers that specify size, extent, position, or qualification of objects and concepts.

    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
    NameInMap
    -0.55
    exitRule
    -0.51
    mybatisplus
    -0.47
    ambién
    -0.47
     barbati
    -0.46
     împre
    -0.44
     inhoud
    -0.43
    antaranya
    -0.43
     argint
    -0.43
    cessite
    -0.42
    POSITIVE LOGITS
     brief
    0.46
     mini
    0.46
     Brief
    0.45
     المعيارى
    0.44
    يكب
    0.43
    minecraftforge
    0.40
     sort
    0.40
     Vesti
    0.40
    jsonwebtoken
    0.39
     Web
    0.38
    Activations Density 0.216%

    No Known Activations