© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 31-GEMMASCOPE-RES-16K
    6. 16074
    Prev
    Next
    INDEX
    Explanations

    references to personal experiences and relationships

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

    words and phrases describing physical appearance or body characteristics.

    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
     [*]
    -0.59
    DataAnnotations
    -0.58
     ujednoznacz
    -0.56
    httphttps
    -0.55
    addCriterion
    -0.54
     AssemblyCulture
    -0.54
     Vikipedi
    -0.54
    Autoritní
    -0.53
     pinulongan
    -0.50
    DotNetBar
    -0.50
    POSITIVE LOGITS
     delighted
    1.35
     excited
    1.34
     disappointed
    1.32
     thrilled
    1.28
     amazed
    1.22
     pleased
    1.21
     dismayed
    1.20
    Excited
    1.20
     frustrated
    1.18
     disgusted
    1.18
    Activations Density 0.828%

    No Known Activations