© 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. 90571
    Prev
    Next
    INDEX
    Explanations

    references to software licenses and their stipulations

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

    for the license

    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
     yyr
    -0.68
    adaptiveStyles
    -0.60
    ViewInit
    -0.60
    SourceChecksum
    -0.60
    Cyfarwyddwr
    -0.59
    GenerationType
    -0.58
    tagext
    -0.57
     balas
    -0.56
    LabelTagHelper
    -0.55
    SequentialGroup
    -0.53
    POSITIVE LOGITS
     gezegd
    0.32
     gobiernos
    0.31
     pihaknya
    0.30
     sièges
    0.30
    Kaynakça
    0.29
     dimaksud
    0.29
     pertanto
    0.28
     expérimentés
    0.28
     fået
    0.28
    Notae
    0.28
    Activations Density 0.005%

    No Known Activations