© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 25-GEMMASCOPE-RES-16K
    11. 372
    Prev
    Next
    INDEX
    Explanations

    HTML structural elements and attributes related to forms and buttons

    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
     racine
    -0.49
    final
    -0.48
     CURIAM
    -0.46
    ~,
    -0.45
    statechange
    -0.44
     final
    -0.44
     picked
    -0.43
    goe
    -0.43
    RDP
    -0.43
    Aure
    -0.43
    POSITIVE LOGITS
    setVerticalGroup
    0.81
    SequentialGroup
    0.78
    ">//
    0.67
    WireFormatLite
    0.67
     align
    0.63
    Tembelea
    0.63
    :✨
    0.62
    AsStream
    0.62
    CodedInputStream
    0.61
     newBuilder
    0.61
    Activations Density 0.036%

    No Known Activations