© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 65k
    9. 13-GEMMASCOPE-RES-65K
    11. 6002
    Prev
    Next
    INDEX
    Explanations

    the word "never" in different contexts, indicating a focus on negation or denial

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 13-gemmascope-res-65k
    Configuration
    google/gemma-scope-2b-pt-res/layer_13/width_65k/average_l0_75
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    65,536
    Data Type
    float32
    Hook Name
    blocks.13.hook_resid_post
    Hook Layer
    13
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    raszam
    -0.81
    StateToProps
    -0.76
    KommentareTeilen
    -0.74
     Muffins
    -0.73
    GenerationType
    -0.73
     MPC
    -0.72
     springfox
    -0.71
     PIB
    -0.71
    MPC
    -0.71
     Marsden
    -0.71
    POSITIVE LOGITS
     Never
    1.37
     never
    1.34
     NEVER
    1.30
    NEVER
    1.27
    Never
    1.23
    never
    1.20
     EVER
    1.13
     ever
    1.09
     Ever
    1.02
     Neve
    0.97
    Activations Density 0.017%

    No Known Activations