© 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
    4. Residual Stream - 16k
    5. 23-GEMMASCOPE-RES-16K
    6. 2230
    Prev
    Next
    INDEX
    Explanations

    content related to scientific research and patents involving compositions or formulations for treatments

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 23-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_23/width_16k/average_l0_120
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.23.hook_resid_post
    Hook Layer
    23
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     ProtoMessage
    -0.84
     CreateTagHelper
    -0.72
     Roskov
    -0.65
    oredCriteria
    -0.62
    MessageOf
    -0.58
    isContained
    -0.57
     للاسماء
    -0.56
    rungsseite
    -0.55
    eramente
    -0.55
    linawan
    -0.55
    POSITIVE LOGITS
     Another
    0.50
    Another
    0.47
     Autre
    0.44
     Similar
    0.43
    Afterwards
    0.40
    另一
    0.40
     Afterwards
    0.39
     Other
    0.39
    Similar
    0.38
    another
    0.38
    Activations Density 0.583%

    No Known Activations