© 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. 7605
    Prev
    Next
    INDEX
    Explanations

    references to systems, features, and processes related to services and applications

    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
    InjectAttribute
    -0.73
     intptr
    -0.72
    OGND
    -0.61
    TagMode
    -0.61
    nonatomic
    -0.60
     estekak
    -0.53
    HideFlags
    -0.51
    ServletConfig
    -0.50
    RegressionTest
    -0.50
    OwnProperty
    -0.47
    POSITIVE LOGITS
     please
    1.71
     check
    1.59
     try
    1.53
     consider
    1.52
     remember
    1.51
     look
    1.43
     don
    1.39
     see
    1.38
     ask
    1.38
     keep
    1.33
    Activations Density 0.991%

    No Known Activations