© 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. 16047
    Prev
    Next
    INDEX
    Explanations

    references to position and configuration, particularly related to central or middle placements

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

    spatial positioning terms like "middle," "center," "top," "bottom," and directional descriptions in layouts or diagrams.

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi

    the word "middle" and surrounding context about finding balance or moderation.

    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
    orsese
    -0.28
     juri
    -0.28
    шкин
    -0.27
    MenuView
    -0.27
     stampa
    -0.26
     listings
    -0.25
     Reach
    -0.24
     rues
    -0.24
    ombra
    -0.24
    髦
    -0.24
    POSITIVE LOGITS
     center
    2.34
     centre
    2.23
     central
    2.16
     middle
    2.11
    centre
    1.95
    center
    1.93
    central
    1.91
     centrale
    1.91
    middle
    1.88
     centrally
    1.88
    Activations Density 0.795%

    No Known Activations