© 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. 24-GEMMASCOPE-RES-16K
    11. 14331
    Prev
    Next
    INDEX
    Explanations

    statements about medical conditions and their associations with various factors

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    studies or research

    np_acts-logits-general · gemini-2.0-flash

    studies and evidence

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 24-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_24/width_16k/average_l0_73
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.hook_resid_post
    Hook Layer
    24
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    tagHelperRunner
    -0.86
    SequentialGroup
    -0.71
     bezeichneter
    -0.69
    FormTagHelper
    -0.68
     protoimpl
    -0.65
    PropertyChanged
    -0.64
    Tikang
    -0.63
    MigrationBuilder
    -0.61
     actionPerformed
    -0.59
     useAppContext
    -0.57
    POSITIVE LOGITS
     studies
    1.55
    studies
    1.13
     research
    1.10
     STUDIES
    0.97
     Studies
    0.97
    Studies
    0.96
     literature
    0.95
     evidence
    0.95
     études
    0.95
     scientific
    0.93
    Activations Density 1.132%

    No Known Activations