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 - 16k
    5. 31-GEMMASCOPE-RES-16K
    6. 9303
    Prev
    Next
    INDEX
    Explanations

    specific scientific or ecological terms related to infections and archaeological artifacts

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

    scientific and technical writing, particularly content related to scientific research, biological terminology, and formal academic documentation.

    oai_token-act-pair · claude-4-5-haikuTriggered by @emiglarou
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 31-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_31/width_16k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.31.hook_resid_post
    Hook Layer
    31
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     envisaged
    -0.51
     Parlamento
    -0.46
    XmlAccessorType
    -0.40
    COLOUR
    -0.40
    -£
    -0.39
     Organisations
    -0.39
     Consultancy
    -0.38
     parlamento
    -0.38
    Colour
    -0.38
    Expiry
    -0.37
    POSITIVE LOGITS
    在美国
    0.97
     Ohio
    0.81
     Delaware
    0.80
     미국
    0.79
    Ohio
    0.79
     Pennsylvania
    0.78
     American
    0.77
    Illinois
    0.77
     美国
    0.77
    美国
    0.76
    Activations Density 0.633%

    No Known Activations