© 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. 400
    Prev
    Next
    INDEX
    Explanations

    mathematical expressions and technical details related to algorithms and data structures

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

    Numbers followed by units of measure

    np_acts-logits-general · gemini-2.0-flash

    technical terms and specific words

    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
    évaluateur
    -0.35
    .*")]
    -0.31
    exitRule
    -0.31
     conde
    -0.29
     produisons
    -0.29
    geli
    -0.27
     rep
    -0.27
    StringCopy
    -0.27
    行
    -0.27
    taxonomy
    -0.27
    POSITIVE LOGITS
     autorytatywna
    0.69
    Dtor
    0.65
    RegressionTest
    0.57
     disambiguazione
    0.53
    ostante
    0.53
    __':
    0.52
     <<<<<<<<<<<<<<
    0.51
    IUrlHelper
    0.49
    verwijspagina
    0.48
    dotto
    0.48
    Activations Density 2.277%

    No Known Activations