© 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. 13849
    Prev
    Next
    INDEX
    Explanations

    references to multiple entities or groups

    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
    RectangleBorder
    -0.54
     TextInputType
    -0.53
    Portály
    -0.52
    IconModule
    -0.50
     Inscrivez
    -0.49
    inputType
    -0.48
     rêves
    -0.48
    MemoryWarning
    -0.47
     Atkinson
    -0.47
     Diseño
    -0.47
    POSITIVE LOGITS
     several
    1.01
     Several
    0.94
    Several
    0.93
    several
    0.89
     dozen
    0.82
     plusieurs
    0.71
    几
    0.71
     few
    0.70
     mehrere
    0.69
     Plusieurs
    0.69
    Activations Density 0.081%

    No Known Activations