© 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
    4. Residual Stream - 16k
    5. 3-GEMMASCOPE-RES-16K
    6. 5792
    Prev
    Next
    INDEX
    Explanations

    references to different forms of fiction

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 3-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_3/width_16k/average_l0_90
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.hook_resid_post
    Hook Layer
    3
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Dokumentation
    -0.43
     revue
    -0.43
     AGUA
    -0.40
     Ausstellung
    -0.39
    ximately
    -0.38
     COUN
    -0.38
     dismissal
    -0.38
    ▂
    -0.38
     što
    -0.38
     PUBLICATIONS
    -0.37
    POSITIVE LOGITS
     fiction
    1.77
     Fiction
    1.51
    Fiction
    1.39
    fiction
    1.38
     FICTION
    1.21
     ficción
    1.20
     fictional
    1.19
     myth
    1.10
     fic
    1.02
    Fic
    0.99
    Activations Density 0.099%

    No Known Activations