© 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. 20-GEMMASCOPE-RES-16K
    6. 938
    Prev
    Next
    INDEX
    Explanations

    terms related to changes and effects in biological measurements and conditions

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

    scientific and statistical terms related to measurements and data variation.

    oai_token-act-pair · claude-3-5-haiku-20241022Triggered by @neilrathi
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_20/width_16k/average_l0_68
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     McKenna
    -0.36
     to
    -0.31
     clearly
    -0.30
     and
    -0.30
    /
    -0.29
     McM
    -0.29
     McManus
    -0.28
     Hay
    -0.27
    手を
    -0.27
     пусты
    -0.27
    POSITIVE LOGITS
     ujednoznacz
    0.98
    JspWriter
    0.94
     disambiguazione
    0.85
     snippetHide
    0.85
     deſſen
    0.79
     surla
    0.74
    __(/*!
    0.74
    posedge
    0.73
     &___
    0.72
    Tikang
    0.72
    Activations Density 0.549%

    No Known Activations