© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 31-GEMMASCOPE-RES-16K
    6. 10918
    Prev
    Next
    INDEX
    Explanations

    occurrences of "Dark Matter" and related phrases in context

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

    The neuron detects the phrase "Dark Matter" and related physics/astronomy terminology, with highest activation on the word "Dark".

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

    the phrase "Dark Matter" across diverse document types and contexts.

    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
     חיצוניים
    -0.60
    ########.
    -0.59
    StructEnd
    -0.58
    +#+#
    -0.58
     surla
    -0.57
    \{\\
    -0.56
    ConstraintMaker
    -0.55
    httphttps
    -0.54
    InitVars
    -0.54
    SharedDtor
    -0.52
    POSITIVE LOGITS
     Dark
    0.77
     dark
    0.72
    Dark
    0.69
     DARK
    0.65
    DARK
    0.58
    dark
    0.57
     oscuro
    0.53
     Dar
    0.53
     matter
    0.48
     darker
    0.47
    Activations Density 0.087%

    No Known Activations