© 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-IT
    4. Residual Stream - 131k
    5. 9-GEMMASCOPE-RES-131K
    6. 66278
    Prev
    Next
    INDEX
    Explanations

    instances of the word "threaten" and its variations

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

    making threats

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 9-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_9/width_131k/average_l0_121
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.9.hook_resid_post
    Hook Layer
    9
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     mukana
    -0.52
     deberes
    -0.50
    rungsseite
    -0.48
     lisäksi
    -0.47
     hänen
    -0.44
     său
    -0.41
     dumne
    -0.41
    Смотрите
    -0.40
     InputDecoration
    -0.40
     høre
    -0.40
    POSITIVE LOGITS
     threaten
    1.63
     threatened
    1.63
     threatening
    1.54
     threatens
    1.46
    threatening
    1.30
     Threatened
    1.23
     amenaz
    1.19
     menac
    1.04
    threat
    1.03
    Threat
    0.98
    Activations Density 0.005%

    No Known Activations