© 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. 12149
    Prev
    Next
    INDEX
    Explanations

    instances of the word "push" and its variants, indicating a focus on forceful or motivating actions

    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
     ""}
    -0.53
    instancetype
    -0.52
    unum
    -0.52
    hops
    -0.49
     graça
    -0.48
     препратки
    -0.48
    ecuzione
    -0.47
    ]]]
    -0.47
    XmlAccessorType
    -0.47
    клопе
    -0.46
    POSITIVE LOGITS
     aside
    0.86
     buttons
    0.73
     against
    0.70
     Buttons
    0.67
    button
    0.67
     boundaries
    0.65
    Against
    0.64
    buttons
    0.64
    against
    0.64
     button
    0.63
    Activations Density 0.188%

    No Known Activations