© 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. 18-GEMMASCOPE-RES-16K
    11. 4812
    Prev
    Next
    INDEX
    Explanations

    data-related terminology and concepts

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

    Data analysis and analytics

    np_acts-logits-general · gemini-2.0-flash

    data analysis and analytics

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.hook_resid_post
    Hook Layer
    18
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     transfieras
    -0.57
    principalColumn
    -0.56
    RectangleBorder
    -0.55
    igshid
    -0.54
     photographed
    -0.54
    HttpDelete
    -0.53
     ratification
    -0.53
    XmlAccessorType
    -0.52
     organizer
    -0.51
    ();)
    -0.51
    POSITIVE LOGITS
     data
    1.03
     analytics
    0.99
     analysts
    0.94
     analysis
    0.93
     Data
    0.92
     analyses
    0.89
     Analytics
    0.88
     datasets
    0.84
     analyst
    0.82
     statistical
    0.81
    Activations Density 0.530%

    No Known Activations