© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    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. 115131
    Prev
    Next
    INDEX
    Explanations

    geographical features and descriptions related to places, particularly islands and terrains

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

    spatial position and environment

    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
     senhor
    -0.35
     calendriers
    -0.34
    呢
    -0.33
     cherchez
    -0.33
     prog
    -0.33
    脲
    -0.31
     лъ
    -0.31
    ImageIO
    -0.31
    őle
    -0.30
    ROIT
    -0.29
    POSITIVE LOGITS
    featureID
    0.60
     Administrativna
    0.58
    IntoConstraints
    0.57
    MigrationBuilder
    0.56
     nakalista
    0.51
    ьаж
    0.51
     geographically
    0.48
     فريبيس
    0.48
    Synonymes
    0.47
     AutoMapper
    0.47
    Activations Density 0.030%

    No Known Activations