© 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. 3-GEMMASCOPE-RES-16K
    6. 11802
    Prev
    Next
    INDEX
    Explanations

    attributes related to access control in programming

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 3-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_3/width_16k/average_l0_59
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.hook_resid_post
    Hook Layer
    3
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ViewFeatures
    -0.69
     Italijani
    -0.65
    tagext
    -0.63
    ولايات
    -0.58
     المعيارى
    -0.57
    OnItem
    -0.56
    oa̍t
    -0.56
     menac
    -0.54
     تعدى
    -0.54
     AssemblyProduct
    -0.53
    POSITIVE LOGITS
     readonly
    3.83
    readonly
    3.04
    ReadOnly
    1.51
    readOnly
    1.23
    setEditable
    0.73
     setLoading
    0.70
     WebDriverWait
    0.67
     Readiness
    0.65
     ReSharper
    0.64
    )":
    0.64
    Activations Density 0.037%

    No Known Activations