Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 11-GEMMASCOPE-RES-16K
    6. 7451
    Prev
    Next
    INDEX
    Explanations

    places, events, or significant locations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 11-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_11/width_16k/average_l0_80
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.11.hook_resid_post
    Hook Layer
    11
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    addCriterion
    -0.89
    providedIn
    -0.80
    StructEnd
    -0.79
    RenderAtEndOf
    -0.79
     doubtnut
    -0.77
     BoxDecoration
    -0.77
     GoogleFonts
    -0.71
    ModelBuilder
    -0.71
    ſelves
    -0.68
     AssemblyCulture
    -0.68
    POSITIVE LOGITS
     where
    0.51
     tempat
    0.48
    #+#
    0.43
     
    0.39
    IntoConstraints
    0.37
     listening
    0.36
    ResponseWriter
    0.36
    where
    0.35
     où
    0.35
     thanks
    0.35
    Activations Density 0.889%

    No Known Activations