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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 9-GEMMASCOPE-RES-16K
    6. 9240
    Prev
    Next
    INDEX
    Explanations

    concepts and terms related to fixed attributes or measurements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    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
    TagMode
    -0.61
    awaiter
    -0.53
    interopRequire
    -0.52
    ThroughAttribute
    -0.51
    脚注の使い方
    -0.49
    AnimationsModule
    -0.49
     lenker
    -0.47
    fontFamily
    -0.46
    splitlines
    -0.46
    TagHelpers
    -0.46
    POSITIVE LOGITS
     fixed
    2.25
     Fixed
    2.08
    fixed
    2.05
    Fixed
    2.05
     FIXED
    1.89
    FIXED
    1.73
     fijo
    1.70
    固定
    1.61
     固定
    1.54
     fija
    1.53
    Activations Density 0.351%

    No Known Activations