© 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. 11901
    Prev
    Next
    INDEX
    Explanations

    references to social policies or issues related to governance and the consequences of actions

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

    sequences describing potential negative consequences or risks of actions.

    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
     approximately
    -0.45
     Approximately
    -0.43
     both
    -0.43
    (?)
    -0.43
     także
    -0.41
    both
    -0.41
     oraz
    -0.39
     including
    -0.39
    approximately
    -0.39
    Approximately
    -0.39
    POSITIVE LOGITS
     magari
    0.90
     somebody
    0.83
     someone
    0.81
     XYZ
    0.76
     للاسماء
    0.75
    somebody
    0.75
     vaikka
    0.72
    someone
    0.72
    majánló
    0.71
    某个
    0.71
    Activations Density 0.826%

    No Known Activations