© 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. 13469
    Prev
    Next
    INDEX
    Explanations

    quantifiable measurements, particularly in mathematical or data contexts

    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
     يتيمه
    -0.63
    ValueStyle
    -0.59
     linkovi
    -0.59
    bkz
    -0.58
     OMITBAD
    -0.56
    ITest
    -0.56
     Charge
    -0.55
     متعلقه
    -0.55
    ificato
    -0.55
     sumpay
    -0.54
    POSITIVE LOGITS
    kháu
    0.61
     amount
    0.60
    awtextra
    0.59
    iomanip
    0.58
    DockStyle
    0.55
     time
    0.54
    Демографія
    0.54
     usize
    0.52
    autoIncrement
    0.51
    ISupport
    0.51
    Activations Density 1.917%

    No Known Activations