© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 31-GEMMASCOPE-RES-16K
    11. 12092
    Prev
    Next
    INDEX
    Explanations

    commands related to API interactions and configurations

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

    indentation and whitespace tokens at the beginning of code lines.

    oai_token-act-pair · claude-4-5-haikuTriggered by @emiglarou
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 31-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_31/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.31.hook_resid_post
    Hook Layer
    31
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    rrggbb
    -0.35
     siguran
    -0.34
    ONOMY
    -0.34
     doGet
    -0.33
     escase
    -0.33
     picioare
    -0.32
     značky
    -0.32
     remercier
    -0.32
     możliwości
    -0.32
     efectivamente
    -0.32
    POSITIVE LOGITS
     pass
    0.86
     Pass
    0.76
     PASS
    0.75
    pass
    0.74
    Pass
    0.70
     passes
    0.69
     passage
    0.68
    MLLoader
    0.65
     passing
    0.65
    rungsseite
    0.65
    Activations Density 0.066%

    No Known Activations