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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 117302
    Prev
    Next
    INDEX
    Explanations

    code-related terms and structures

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

    Identifiers, variables, or references being accessed in code across different programming languages and contexts, often appearing as part of a qualified name or being operated upon.

    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
     helicópter
    -0.40
     Warenkorb
    -0.38
     helicóptero
    -0.38
     sitä
    -0.36
    ษัท
    -0.36
     bolsillos
    -0.36
     encantado
    -0.36
     bolsillo
    -0.35
    <!--
    -0.35
     assuré
    -0.35
    POSITIVE LOGITS
     '\\;'
    0.73
     resourceCulture
    0.56
     TextInputType
    0.52
    AndroidJUnit
    0.52
    expandindo
    0.51
    WriteTagHelper
    0.51
    openConnection
    0.50
    
    0.50
     GenerationType
    0.49
    ArrowToggle
    0.49
    Activations Density 0.164%

    No Known Activations