Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 25-GEMMASCOPE-RES-16K
    6. 15535
    Prev
    Next
    INDEX
    Explanations

    structured information that indicates a clear introduction to a topic

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 25-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_25/width_16k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.hook_resid_post
    Hook Layer
    25
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    principalColumn
    -0.68
    kháu
    -0.64
    EndGlobalSection
    -0.63
     للاسماء
    -0.63
    WriteBarrier
    -0.62
    parsedMessage
    -0.61
    IntoConstraints
    -0.60
     snippetHide
    -0.57
    TextBoxColumn
    -0.56
     مشين
    -0.56
    POSITIVE LOGITS
     telefónica
    0.42
     Económica
    0.41
    antaranya
    0.41
    rsiniz
    0.40
     bancaria
    0.39
    klere
    0.39
     варто
    0.39
     aikaa
    0.39
     calorías
    0.37
     práci
    0.37
    Activations Density 5.341%

    No Known Activations