© 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. 9002
    Prev
    Next
    INDEX
    Explanations

    actions related to submission and publication processes

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

    past tense verbs or completed actions, particularly those indicating arrival, introduction, or submission.

    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
     when
    -0.67
     когда
    -0.61
     sobald
    -0.57
     quando
    -0.55
     înainte
    -0.54
    当
    -0.53
    when
    -0.52
    當
    -0.51
     cuando
    -0.50
     while
    -0.50
    POSITIVE LOGITS
    RegistryLite
    0.56
     xong
    0.48
     nanti
    0.47
    Références
    0.47
     decides
    0.44
     Vereine
    0.43
    riever
    0.43
    niająca
    0.42
     erstmals
    0.42
    初めて
    0.41
    Activations Density 0.500%

    No Known Activations