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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B-IT
    4. Residual Stream - 16k
    5. 20-GEMMASCOPE-RES-16K
    6. 8214
    Prev
    Next
    INDEX
    Explanations

    specific geographic locations or administrative divisions

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

    or abbreviations followed by a period

    np_acts-logits-general · gemini-2.0-flash

    names and abbreviations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_16k/average_l0_91
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    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
    DataAnnotations
    -0.47
    basicConfig
    -0.47
    JAKARTA
    -0.46
     ultimate
    -0.45
     Arlington
    -0.45
     Williams
    -0.45
    printStackTrace
    -0.45
    Dunn
    -0.44
     Dunn
    -0.44
     UnityEditor
    -0.44
    POSITIVE LOGITS
    oso
    0.63
    og
    0.62
    oto
    0.61
    oz
    0.59
    od
    0.59
    odo
    0.58
    oyo
    0.58
    oid
    0.58
    ode
    0.58
    oy
    0.58
    Activations Density 1.670%

    No Known Activations