© 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-2-9B-IT
    4. Residual Stream - 131k
    5. 20-GEMMASCOPE-RES-131K
    6. 126390
    Prev
    Next
    INDEX
    Explanations

    information about restrictions and requirements related to accommodations

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

    arrival, guests, children

    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-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_131k/average_l0_81
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    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
    backtracking
    -0.43
     autorytatywna
    -0.40
     ubiquitous
    -0.36
    TargetException
    -0.35
    rungsseite
    -0.35
     collaborations
    -0.34
    Elsewhere
    -0.34
    istoitu
    -0.33
     оригіналу
    -0.33
     responsive
    -0.33
    POSITIVE LOGITS
     ModelRenderer
    0.51
    épaisseur
    0.46
     Vikipedi
    0.45
    softc
    0.44
     lccn
    0.44
    IsUnicode
    0.44
     }{@
    0.43
     OMITBAD
    0.43
    ⅘
    0.41
    EndGlobalSection
    0.40
    Activations Density 0.002%

    No Known Activations