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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B-IT
    4. Residual Stream - 16k
    5. 20-GEMMASCOPE-RES-16K
    6. 1063
    Prev
    Next
    INDEX
    Explanations

    correlations related to psychological and physiological assessments

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

    Correlation between variables

    np_acts-logits-general · gemini-2.0-flash

    correlation with severity

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_16k/average_l0_91
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    httphttps
    -0.62
    WriteTagHelper
    -0.42
    jstor
    -0.42
     estekak
    -0.41
    __':
    
    -0.39
     informée
    -0.38
    tagHelperRunner
    -0.38
    aarrggbb
    -0.37
    compar
    -0.36
    новништво
    -0.36
    POSITIVE LOGITS
    ViewStyle
    0.43
    DataAnnotations
    0.40
     measures
    0.40
     <<<<<<<<<<<<<<
    0.40
     protested
    0.40
     GetEnumerator
    0.39
    TextStyle
    0.38
     Cor
    0.36
     correlates
    0.36
     Trooper
    0.36
    Activations Density 1.539%

    No Known Activations