© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 31-GEMMASCOPE-RES-16K
    6. 4627
    Prev
    Next
    INDEX
    Explanations

    elements related to fairy tales and storytelling

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

    fairy tale and fantasy-related content, particularly words and phrases associated with magical stories, enchanted characters, and fantastical narratives.

    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
    SequentialGroup
    -0.65
    SharedDtor
    -0.60
    ंदीखरीदारी
    -0.57
    Tikang
    -0.57
    posedge
    -0.57
     ब्रेकडाउन
    -0.56
     testigo
    -0.54
    InputTagHelper
    -0.54
    Personendaten
    -0.54
     uVar
    -0.53
    POSITIVE LOGITS
     fairy
    1.38
     Fairy
    1.20
     fairytale
    1.09
    Fairy
    1.02
     Märchen
    1.00
    fairy
    0.98
     Cinderella
    0.94
     princess
    0.82
     сказ
    0.81
     fairies
    0.80
    Activations Density 0.248%

    No Known Activations