© 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. 5-GEMMASCOPE-RES-16K
    6. 457
    Prev
    Next
    INDEX
    Explanations

    references to protocol and message structures in programming languages, particularly related to Protobuf

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    programming constructs and elements related to protocol buffers

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.5.hook_resid_post
    Hook Layer
    5
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    principalColumn
    -0.86
    ftagPool
    -0.84
    ագրություններ
    -0.80
    ActionCreators
    -0.76
     doInBackground
    -0.75
     resourceCulture
    -0.73
     onAnimation
    -0.72
    twimg
    -0.69
    AsyncResult
    -0.68
    AndroidJUnit
    -0.67
    POSITIVE LOGITS
     наук
    0.55
    __[
    0.52
    ariot
    0.51
     aan
    0.51
    TERY
    0.50
    ريل
    0.49
     Kramer
    0.49
    ven
    0.48
    GEBURTSDATUM
    0.48
    γά
    0.48
    Activations Density 0.021%

    No Known Activations