© 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. 12-GEMMASCOPE-RES-16K
    11. 5029
    Prev
    Next
    INDEX
    Explanations

    negatively charged emotional expressions related to abandonment and injustice

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 12-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_12/width_16k/average_l0_130
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.hook_resid_post
    Hook Layer
    12
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    <bos>
    -0.31
    élément
    -0.26
    </h1>
    -0.25
     üzerinden
    -0.25
     Lac
    -0.25
     volunt
    -0.23
    UNTE
    -0.23
    tonode
    -0.23
     language
    -0.22
     répé
    -0.22
    POSITIVE LOGITS
    uxxxx
    1.09
    Referencies
    0.91
    -------
    0.77
     <<<<<<<<<<<<<<
    0.72
     للمعارف
    0.70
     surla
    0.69
    httphttps
    0.69
    RegressionTest
    0.68
    нгред
    0.68
    OOTDTY
    0.66
    Activations Density 2.915%

    No Known Activations