© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 9-GEMMASCOPE-RES-16K
    11. 8688
    Prev
    Next
    INDEX
    Explanations

    scientific terms and concepts related to plasma physics

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

    This neuron detects terms related to plasma physics, including words like "plasma", "ions", "electrons", and "particles".

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 9-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_9/width_16k/average_l0_100
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.9.hook_resid_post
    Hook Layer
    9
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     виправивши
    -0.36
    Enllaços
    -0.34
     пло
    -0.31
    /////
    -0.31
    acyj
    -0.29
     prácti
    -0.29
    capa
    -0.28
    łod
    -0.28
     jou
    -0.28
     dermatitis
    -0.28
    POSITIVE LOGITS
    MigrationBuilder
    0.71
    portál
    0.64
    featureID
    0.62
     surla
    0.60
    __()
    0.60
     Италијани
    0.57
    Abitanti
    0.56
    ьаж
    0.56
    FormTagHelper
    0.56
    parsedMessage
    0.54
    Activations Density 0.158%

    No Known Activations