© 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-IT
    7. Residual Stream - 16k
    9. 20-GEMMASCOPE-RES-16K
    11. 1310
    Prev
    Next
    INDEX
    Explanations

    references to iconic fictional detectives

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

    Mystery, crime, and detective themes

    np_acts-logits-general · gemini-2.0-flash

    detective crime CSI FBI mysteries murder

    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-16k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_16k/average_l0_91
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    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
    zeits
    -0.32
     пода
    -0.32
     pozy
    -0.30
     createStore
    -0.30
     aguj
    -0.30
    Demografie
    -0.29
     esterni
    -0.29
     mod
    -0.29
     anyway
    -0.28
    باره
    -0.28
    POSITIVE LOGITS
     detective
    0.72
     detectives
    0.69
    nsics
    0.63
    detective
    0.63
     Sherlock
    0.63
     Detective
    0.61
    Detective
    0.58
     ComVisible
    0.57
     Efq
    0.57
     crime
    0.56
    Activations Density 0.237%

    No Known Activations