© 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. 40-GEMMASCOPE-RES-16K
    11. 5322
    Prev
    Next
    INDEX
    Explanations

    significant emotional moments and character dynamics in storytelling

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 40-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_40/width_16k/average_l0_125
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.40.hook_resid_post
    Hook Layer
    40
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    GOTREF
    -0.54
    Parameteri
    -0.42
    лтамалар
    -0.42
     šķ
    -0.42
    AccessorTable
    -0.42
    GTCX
    -0.41
    PreferredItem
    -0.40
    canestro
    -0.40
     proprietà
    -0.37
    ValueStyle
    -0.37
    POSITIVE LOGITS
     episode
    2.23
     ep
    1.97
     Episode
    1.93
     episodes
    1.87
    episode
    1.81
     Ep
    1.79
    Episode
    1.74
     epis
    1.68
     eps
    1.67
     EPISODE
    1.67
    Activations Density 0.459%

    No Known Activations