© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 4726
    Prev
    Next
    INDEX
    Explanations

    references to agency and decision-making regarding funding and governance

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

    phrases where someone is given or provided something, particularly in contexts involving agency, information, or opportunity.

    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
    Aktualisiert
    -0.46
    Tikang
    -0.46
     JpaRepository
    -0.44
    rawDesc
    -0.42
    ագրություններ
    -0.39
     announcement
    -0.37
     tramo
    -0.36
    joke
    -0.36
    RTLD
    -0.35
    İstinadlar
    -0.35
    POSITIVE LOGITS
     reaſon
    0.66
     plenty
    0.62
     reafon
    0.59
     something
    0.59
     some
    0.57
     a
    0.55
     ample
    0.54
     permission
    0.54
     mulighed
    0.54
     the
    0.52
    Activations Density 0.149%

    No Known Activations