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 - 131k
    5. 20-GEMMASCOPE-RES-131K
    6. 68960
    Prev
    Next
    INDEX
    Explanations

    terminology related to migration and movement

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

    migration

    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-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_131k/average_l0_81
    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
     oldValue
    -0.57
    setupUi
    -0.49
    Else
    -0.48
    anum
    -0.47
    setLength
    -0.47
    Box
    -0.45
    kapnya
    -0.45
    fun
    -0.45
    <bos>
    -0.44
    Spez
    -0.44
    POSITIVE LOGITS
     migration
    1.19
     Migration
    1.16
     migrate
    1.07
     Migrate
    1.05
    Migration
    1.02
     migrations
    0.95
    migration
    0.94
     migra
    0.93
     migrating
    0.91
     Mig
    0.88
    Activations Density 0.007%

    No Known Activations