© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 21-GEMMASCOPE-RES-16K
    6. 13976
    Prev
    Next
    INDEX
    Explanations

    numerical patterns and sequences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 21-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_21/width_16k/average_l0_129
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.hook_resid_post
    Hook Layer
    21
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Eilish
    -0.57
    ValueStyle
    -0.56
    Datuak
    -0.56
     المعيارى
    -0.53
    Архівовано
    -0.52
    inSlope
    -0.51
     banquet
    -0.49
     chances
    -0.49
    السكان
    -0.49
     chance
    -0.49
    POSITIVE LOGITS
     stanga
    0.38
     мәкал
    0.37
     umane
    0.37
    Rptr
    0.37
     Woodward
    0.36
     bună
    0.36
     transférez
    0.35
    inverted
    0.34
    tranno
    0.34
     terang
    0.34
    Activations Density 1.042%

    No Known Activations