© 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-2-2B
    4. Residual Stream - 16k
    5. 25-GEMMASCOPE-RES-16K
    6. 10676
    Prev
    Next
    INDEX
    Explanations

    elements related to health care assessment and research validity

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 25-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_25/width_16k/average_l0_116
    Prompts (Dashboard)
    36,864 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
    transQ
    -0.68
    RegistryLite
    -0.66
     الحره
    -0.65
    
    -0.64
     المعيارى
    -0.61
    LookAnd
    -0.60
    MigrationBuilder
    -0.58
     Hivatalos
    -0.53
    ApiModelProperty
    -0.52
    באנגלית
    -0.52
    POSITIVE LOGITS
     duration
    1.08
     type
    1.06
     nature
    1.02
     types
    0.98
     dates
    0.97
     number
    0.94
     how
    0.94
     length
    0.93
    nature
    0.89
     date
    0.88
    Activations Density 0.738%

    No Known Activations