© 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. 7629
    Prev
    Next
    INDEX
    Explanations

    references to scientific theories and their relationship to empirical evidence

    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
     StyleSheet
    -0.66
     protoimpl
    -0.63
     ModelExpression
    -0.62
    Pautan
    -0.61
    CodedInputStream
    -0.60
    matchCondition
    -0.57
     nakalista
    -0.57
    sendRedirect
    -0.57
     snippetHide
    -0.55
    aspectj
    -0.54
    POSITIVE LOGITS
     scientific
    1.19
     science
    1.17
     scientists
    1.07
    science
    1.03
     Scientific
    1.02
    scientific
    1.01
    scienti
    0.99
    Scientific
    0.98
     Science
    0.98
     scientifique
    0.98
    Activations Density 0.473%

    No Known Activations