© 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. 31-GEMMASCOPE-RES-16K
    11. 3627
    Prev
    Next
    INDEX
    Explanations

    elements related to nature, culture, and local events

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

    natural or physical objects and elements found in scenic or outdoor environments.

    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
     Profile
    -0.30
     intends
    -0.30
     Bull
    -0.29
     Powered
    -0.29
     PST
    -0.29
     seniority
    -0.28
     BULL
    -0.28
    cmds
    -0.28
     Institution
    -0.27
     via
    -0.27
    POSITIVE LOGITS
     everywhere
    1.55
    everywhere
    1.44
     Everywhere
    1.30
    Everywhere
    1.29
     abound
    1.20
     galore
    1.15
     abounds
    1.15
     ovunque
    1.13
     überall
    1.13
     plentiful
    1.03
    Activations Density 0.404%

    No Known Activations