© 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. 27-GEMMASCOPE-RES-16K
    6. 10167
    Prev
    Next
    INDEX
    Explanations

    topics related to health improvement and behavioral change interventions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 27-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_27/width_16k/average_l0_118
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.27.hook_resid_post
    Hook Layer
    27
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     للاسماء
    -0.44
    complexContent
    -0.42
     Biôgrafia
    -0.40
    Välislingid
    -0.37
    ToBounds
    -0.36
     Vikipedi
    -0.36
    giarism
    -0.35
    farwyddwr
    -0.35
    Datuak
    -0.35
     Económica
    -0.34
    POSITIVE LOGITS
     behavioural
    0.84
     behavioral
    0.82
     behavior
    0.75
     behaviour
    0.73
     change
    0.70
    behavioral
    0.69
     BEHAVIOR
    0.69
     Behavior
    0.65
     Behavioral
    0.65
     Behaviour
    0.64
    Activations Density 0.675%

    No Known Activations