© 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. 20-GEMMASCOPE-RES-131K
    6. 102319
    Prev
    Next
    INDEX
    Explanations

    words and phrases related to haunting or supernatural themes

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

    haunted, plagued, tormented

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_131k/average_l0_81
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ########.
    -0.63
    Personendaten
    -0.60
    OGND
    -0.56
     للاسماء
    -0.54
    ViewInit
    -0.52
     jspb
    -0.52
    mrb
    -0.51
    devamını
    -0.50
     oprot
    -0.50
    fromCharCode
    -0.50
    POSITIVE LOGITS
     haunted
    0.94
    Haunted
    0.93
     haunting
    0.88
     Haunted
    0.84
     haunt
    0.84
     haunts
    0.71
     plagued
    0.54
    ciąż
    0.54
     Hunt
    0.44
     infección
    0.43
    Activations Density 0.005%

    No Known Activations