© 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. 31-GEMMASCOPE-RES-16K
    11. 9486
    Prev
    Next
    INDEX
    Explanations

    expressions of excitement and engagement

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

    punctuation marks and contractions, particularly apostrophes and exclamation marks used in excited or emphatic expressions.

    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
    WriteBarrier
    -0.68
    interopRequire
    -0.58
    ValueStyle
    -0.58
     viewDidLoad
    -0.54
    AnchorStyles
    -0.53
    RegressionTest
    -0.52
    IVEREF
    -0.52
     invokingState
    -0.51
    DockStyle
    -0.51
     transfieras
    -0.49
    POSITIVE LOGITS
    deviantart
    0.85
     DeviantArt
    0.84
     deviant
    0.78
     devi
    0.72
     deviations
    0.71
     deviation
    0.71
     dA
    0.66
     Deviant
    0.66
     Deviation
    0.65
     Devi
    0.63
    Activations Density 0.171%

    No Known Activations