Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 24-GEMMASCOPE-RES-16K
    6. 1066
    Prev
    Next
    INDEX
    Explanations

    technical terminology related to scientific and technical processes or specifications

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

    before "correction", "research", "analysis", etc

    np_acts-logits-general · gemini-2.0-flash

    technical analysis components

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 24-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_24/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.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
     general
    -0.34
     
    -0.33
     An
    -0.33
     entire
    -0.32
     basic
    -0.32
     most
    -0.31
    An
    -0.31
     great
    -0.31
     [
    -0.31
     full
    -0.29
    POSITIVE LOGITS
     lenker
    0.96
    CppMethod
    0.93
     שוליים
    0.82
    featureID
    0.81
    LookAnd
    0.81
    
    0.75
    enterOuterAlt
    0.74
    Hentet
    0.74
    #+#
    0.74
    TagMode
    0.74
    Activations Density 1.110%

    No Known Activations