© 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
    7. Residual Stream - 16k
    9. 33-GEMMASCOPE-RES-16K
    11. 8315
    Prev
    Next
    INDEX
    Explanations

    elements related to emotional conflict and character relationships in storytelling

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 33-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_33/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.33.hook_resid_post
    Hook Layer
    33
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     cdti
    -0.36
    ekyll
    -0.36
    glVertex
    -0.36
    RegistryLite
    -0.35
    óval
    -0.35
    ależy
    -0.34
    habitude
    -0.34
    inSlope
    -0.34
    exitRule
    -0.34
    ibouti
    -0.33
    POSITIVE LOGITS
     nakalista
    0.62
     Upside
    0.57
     Italijanski
    0.53
     ThemeData
    0.52
     Toto
    0.50
    UnknownFieldSet
    0.48
     MenuView
    0.47
     Apu
    0.46
     LST
    0.46
     Marge
    0.46
    Activations Density 0.204%

    No Known Activations