© 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-2-9B
    7. Residual Stream - 16k
    9. 23-GEMMASCOPE-RES-16K
    11. 9077
    Prev
    Next
    INDEX
    Explanations

    terms related to comparative analysis in biological and mechanical contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 23-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_23/width_16k/average_l0_120
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.23.hook_resid_post
    Hook Layer
    23
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     lata
    -0.34
     angeb
    -0.34
     healthier
    -0.32
     cheaper
    -0.32
     betere
    -0.31
    JsonInclude
    -0.30
    Ligações
    -0.29
    kháu
    -0.29
     happier
    -0.29
    CGRectMake
    -0.29
    POSITIVE LOGITS
     needs
    0.82
     demands
    0.75
     complexities
    0.73
     challenges
    0.70
    Needs
    0.68
     potře
    0.68
    needs
    0.67
     complexity
    0.67
     esigenze
    0.67
     tantangan
    0.66
    Activations Density 0.683%

    No Known Activations