© 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-2-9B
    4. Residual Stream - 16k
    5. 25-GEMMASCOPE-RES-16K
    6. 15386
    Prev
    Next
    INDEX
    Explanations

    technical terms related to power generation and systems

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 25-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_25/width_16k/average_l0_114
    Prompts (Dashboard)
    24,576 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
    SerializedSize
    -0.37
     b
    -0.36
    AutoField
    -0.36
     Concer
    -0.35
    CppMethod
    -0.34
    ^{-\
    -0.33
     chor
    -0.33
     гро
    -0.33
     UIS
    -0.33
    ping
    -0.32
    POSITIVE LOGITS
     ModelExpression
    0.71
     étoient
    0.63
     avoient
    0.59
    GeneratedMessage
    0.57
     dezelve
    0.56
     étoit
    0.55
     picioare
    0.54
    routeProvider
    0.54
     snippetHide
    0.53
    bildēt
    0.52
    Activations Density 1.606%

    No Known Activations