© 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. 16085
    Prev
    Next
    INDEX
    Explanations

    phrases related to controversy and conflict involving social issues

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

    negative or inflammatory language describing harmful, dangerous, or objectionable behavior or conditions.

    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
     adecuadamente
    -0.45
     efficacement
    -0.44
    Kelebihan
    -0.42
     enthusiasm
    -0.41
     Hinweise
    -0.41
     helyzet
    -0.40
     autoestima
    -0.40
    verwijspagina
    -0.40
     conducta
    -0.40
    Vaata
    -0.40
    POSITIVE LOGITS
     dangerous
    0.64
     scary
    0.56
     interesting
    0.56
     exciting
    0.55
     very
    0.54
     extremely
    0.54
     stressful
    0.54
     strange
    0.52
    dangerous
    0.52
     nont
    0.52
    Activations Density 0.653%

    No Known Activations