© 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-2-2B
    4. Residual Stream - 16k
    5. 15-GEMMASCOPE-RES-16K
    6. 1181
    Prev
    Next
    INDEX
    Explanations

    elements related to supernatural or fantastical themes in narratives

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 15-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_15/width_16k/average_l0_78
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.15.hook_resid_post
    Hook Layer
    15
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    restle
    -0.55
    jshint
    -0.49
    EndTag
    -0.49
    pulo
    -0.48
    arschijnlijk
    -0.48
    MethodManager
    -0.47
    randrange
    -0.47
     tuy
    -0.47
     PropertyChanged
    -0.47
    CUIT
    -0.46
    POSITIVE LOGITS
    enderror
    0.59
     otomatig
    0.59
     rând
    0.58
     helft
    0.57
    دانشنامهٔ
    0.56
    seamnă
    0.56
     griega
    0.54
     Houſe
    0.54
     Majefty
    0.54
     poffible
    0.53
    Activations Density 0.158%

    No Known Activations