© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 24-GEMMASCOPE-RES-16K
    11. 1275
    Prev
    Next
    INDEX
    Explanations

    programming terms related to functions and operations on data structures

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

    Code assignments and operations

    np_acts-logits-general · gemini-2.0-flash

    assignment operators and formulas

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 24-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_24/width_16k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.hook_resid_post
    Hook Layer
    24
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    AddTagHelper
    -0.73
     незавершена
    -0.52
    EDEFAULT
    -0.48
     فريبيس
    -0.48
    featureID
    -0.47
     Grüsse
    -0.42
     einiges
    -0.41
    󠁮
    -0.41
     sekal
    -0.41
     excru
    -0.40
    POSITIVE LOGITS
    XmlAccessType
    0.46
     clone
    0.42
     válto
    0.42
     altered
    0.41
    లాలు
    0.41
     updated
    0.41
     становника
    0.39
     الحره
    0.39
    SuspendLayout
    0.39
     unchanged
    0.39
    Activations Density 0.413%

    No Known Activations