© 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. 757
    Prev
    Next
    INDEX
    Explanations

    references to the "Ram" brand, particularly in automotive contexts

    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
    ImageContext
    -0.63
     Chwiliwch
    -0.62
     ModelExpression
    -0.61
    inheritdoc
    -0.59
    EndGlobalSection
    -0.55
    AnimationsModule
    -0.53
    NewUrlParser
    -0.52
    protoc
    -0.52
    Gep
    -0.52
    AndEndTag
    -0.51
    POSITIVE LOGITS
    paging
    0.60
    esses
    0.56
    Autoritní
    0.55
    MessageOf
    0.54
    dane
    0.53
     ewe
    0.51
    page
    0.49
    paged
    0.49
    seys
    0.48
     diarias
    0.47
    Activations Density 0.349%

    No Known Activations