© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 11-GEMMASCOPE-RES-16K
    6. 13644
    Prev
    Next
    INDEX
    Explanations

    elements related to coding and programming structures or functions

    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
     springfox
    -0.61
     åt
    -0.56
    llong
    -0.55
    wns
    -0.55
    EndContext
    -0.51
    ője
    -0.51
    seamnă
    -0.50
    tryk
    -0.50
    ticulate
    -0.49
    epiece
    -0.49
    POSITIVE LOGITS
     dAtA
    0.56
     utafitiHapana
    0.54
    sizeCache
    0.53
    apimachinery
    0.52
    ValueGeneration
    0.52
    ActionCreators
    0.51
     smtplib
    0.51
    posedge
    0.51
     ActiveRecord
    0.50
     onAnimation
    0.50
    Activations Density 0.402%

    No Known Activations