© 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. 16216
    Prev
    Next
    INDEX
    Explanations

    technical terms related to electrical circuits and components

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

    electrical terms related to circuits, voltage, electrodes, and current flow.

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered 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
    脚注の使い方
    -0.68
    帖最后由
    -0.59
    ########.
    -0.58
    𖧹
    -0.56
    raisal
    -0.56
     متعلقه
    -0.56
    يميديا
    -0.55
    ніципалі
    -0.55
    باردا
    -0.54
    <unused21>
    -0.54
    POSITIVE LOGITS
     electrodes
    0.57
     electrode
    0.57
     electric
    0.48
     Electro
    0.46
     lightning
    0.46
     electricity
    0.45
     elekt
    0.43
     electrochemical
    0.43
     Electrode
    0.43
     skin
    0.43
    Activations Density 0.431%

    No Known Activations