© 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. 6-GEMMASCOPE-RES-16K
    6. 11890
    Prev
    Next
    INDEX
    Explanations

    occurrences of annotations and markup related to serialized data structures in a coding context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 6-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_6/width_16k/average_l0_70
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.6.hook_resid_post
    Hook Layer
    6
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     propOrder
    -0.75
    ConstraintMaker
    -0.57
     REMARKS
    -0.55
    IService
    -0.54
    thenReturn
    -0.54
     Polic
    -0.53
    $_['
    -0.52
     OnEnable
    -0.52
    IntoConstraints
    -0.51
    TextSpan
    -0.51
    POSITIVE LOGITS
     fa
    0.68
    antwortung
    0.64
    awaiter
    0.60
     QtGui
    0.60
    glGen
    0.58
    mallows
    0.58
    HasForeignKey
    0.57
     ReactDOM
    0.56
    olson
    0.56
    rovnik
    0.56
    Activations Density 0.006%

    No Known Activations