© 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 - 65k
    5. 13-GEMMASCOPE-RES-65K
    6. 38580
    Prev
    Next
    INDEX
    Explanations

    components related to web frameworks and specifically URL routing

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 13-gemmascope-res-65k
    Configuration
    google/gemma-scope-2b-pt-res/layer_13/width_65k/average_l0_75
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    65,536
    Data Type
    float32
    Hook Name
    blocks.13.hook_resid_post
    Hook Layer
    13
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     HasFactory
    -1.10
     '{@
    -1.05
    NameInMap
    -0.98
     resourceCulture
    -0.96
    ConstraintMaker
    -0.92
     '\\;'
    -0.90
     propOrder
    -0.88
    rungsseite
    -0.85
    曖昧さ回避
    -0.84
    UnusedPrivate
    -0.83
    POSITIVE LOGITS
     EconPapers
    0.59
    hove
    0.56
    ">:
    0.53
    zeb
    0.52
     Catch
    0.50
    exa
    0.50
    ης
    0.49
    tingham
    0.49
     Euph
    0.49
     rotina
    0.49
    Activations Density 0.000%

    No Known Activations