© 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. 9779
    Prev
    Next
    INDEX
    Explanations

    phrases indicating denial or negation

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

    contractions with apostrophes (like "don't", "it's", "I'm").

    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
     exposed
    -0.35
     اقت
    -0.34
     Mandel
    -0.34
     Houghton
    -0.34
    kunft
    -0.33
     intervene
    -0.33
    rantz
    -0.33
     افت
    -0.32
    mand
    -0.32
     Grimal
    -0.32
    POSITIVE LOGITS
    httphttps
    0.71
     contextLoads
    0.63
    oa̍t
    0.63
    tvguidetime
    0.61
     صوتيه
    0.60
     ControllerBase
    0.60
     transfieras
    0.56
    Geplaatst
    0.55
     lenker
    0.54
    ValueStyle
    0.53
    Activations Density 0.052%

    No Known Activations