© 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. 10759
    Prev
    Next
    INDEX
    Explanations

    complex technical terms and specific jargon related to electronics and programming

    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
    kiyor
    -0.63
    intenant
    -0.63
    WriteTagHelper
    -0.63
    nya
    -0.62
    cuador
    -0.58
    ⤹
    -0.56
    llingwood
    -0.56
    dshaw
    -0.55
    ArgumentParser
    -0.52
    ihnachts
    -0.52
    POSITIVE LOGITS
    e
    1.13
    ee
    0.84
    eee
    0.81
    eeee
    0.79
    ie
    0.78
    ede
    0.77
    eeeee
    0.75
    ije
    0.75
    es
    0.74
    eche
    0.74
    Activations Density 2.544%

    No Known Activations