Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B-IT
    4. Residual Stream - 16k
    5. 31-GEMMASCOPE-RES-16K
    6. 16106
    Prev
    Next
    INDEX
    Explanations

    expressions of loud vocalization or outcry

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

    someone is speaking loudly

    np_acts-logits-general · gemini-2.0-flash

    shouting and yelling

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 31-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-it-res/layer_31/width_16k/average_l0_76
    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
    ModelSerializer
    -0.55
     BorderRadius
    -0.50
     BorderSide
    -0.48
    WithIOException
    -0.47
     onPostExecute
    -0.47
     <>",
    -0.46
    weigh
    -0.46
     Weigh
    -0.43
    Weigh
    -0.43
    borderFill
    -0.43
    POSITIVE LOGITS
     shout
    1.81
     shouts
    1.80
     shouting
    1.80
     shouted
    1.76
     yell
    1.67
     yelling
    1.66
     scream
    1.62
     yells
    1.62
     yelled
    1.59
     screaming
    1.53
    Activations Density 0.140%

    No Known Activations