© 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 - 16k
    9. 15-GEMMASCOPE-RES-16K
    11. 10934
    Prev
    Next
    INDEX
    Explanations

    phrases that express suggestions, opinions, and conditional statements related to actions or behaviors

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 15-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_15/width_16k/average_l0_78
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.15.hook_resid_post
    Hook Layer
    15
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     significantly
    -0.42
     kív
    -0.42
     sahiptir
    -0.41
    stone
    -0.40
     démocratique
    -0.40
    Ton
    -0.39
    erca
    -0.39
     substantially
    -0.39
    мен
    -0.38
    に対し
    -0.38
    POSITIVE LOGITS
     fuckin
    0.93
    IntoConstraints
    0.91
    uxxxx
    0.89
    IUrlHelper
    0.88
    MessageTagHelper
    0.86
     fucking
    0.83
    Portale
    0.80
     виправивши
    0.79
    Portail
    0.78
     useStyles
    0.77
    Activations Density 0.307%

    No Known Activations