© 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. 126364
    Prev
    Next
    INDEX
    Explanations

    terms and phrases related to data handling and system configurations

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

    no followed by certain words

    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
    Personendaten
    -0.82
    expandindo
    -0.77
    transQ
    -0.74
     betweenstory
    -0.68
    principalColumn
    -0.60
     Económica
    -0.59
     jspb
    -0.59
    GIVEREF
    -0.58
     ModelExpression
    -0.58
    ukone
    -0.57
    POSITIVE LOGITS
     no
    0.60
    No
    0.57
     No
    0.53
    NoSuchAlgorithm
    0.48
     nop
    0.46
    None
    0.44
     NO
    0.44
    no
    0.44
     none
    0.44
    NoStop
    0.43
    Activations Density 0.033%

    No Known Activations