© 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-IT
    7. Residual Stream - 16k
    9. 20-GEMMASCOPE-RES-16K
    11. 1244
    Prev
    Next
    INDEX
    Explanations

    technical terms related to data processing and calibration in scientific contexts

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

    Scientific data collection terminology

    np_acts-logits-general · gemini-2.0-flash

    data acquisition and scanning

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_16k/average_l0_91
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ">//
    -0.37
    rrggbb
    -0.35
     alugar
    -0.31
     جمله
    -0.30
     giusti
    -0.30
     retenir
    -0.29
     nemlig
    -0.29
     disambiguazione
    -0.29
    bond
    -0.28
    HasAnnotation
    -0.28
    POSITIVE LOGITS
    expandindo
    0.68
    :✨
    0.64
    MessageTagHelper
    0.60
    цездатний
    0.57
     otomatig
    0.54
     session
    0.52
    InitVars
    0.52
    ngOnDestroy
    0.51
     routine
    0.50
     cooldown
    0.50
    Activations Density 0.941%

    No Known Activations