Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 131k
    5. 20-GEMMASCOPE-RES-131K
    6. 105346
    Prev
    Next
    INDEX
    Explanations

    terms related to health, genetics, and diagnostics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-9b-pt-res/layer_20/width_131k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    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
    RTSC
    -0.51
    ApiModelProperty
    -0.40
    \{\\
    -0.40
    ]=>
    -0.39
    WebServlet
    -0.39
    fml
    -0.39
    Cyfeiriadau
    -0.39
    izr
    -0.39
    ToScroll
    -0.38
     Moll
    -0.38
    POSITIVE LOGITS
     issues
    0.53
     elements
    0.49
     चीज़ों
    0.47
     challenges
    0.45
     expressions
    0.45
     ailments
    0.45
     indicators
    0.44
     spørgsmål
    0.44
     questions
    0.44
     markers
    0.44
    Activations Density 0.130%

    No Known Activations