© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 4490
    Prev
    Next
    INDEX
    Explanations

    phrases related to performance assessment and efficiency in various contexts

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

    Follows nouns indicating a change or evaluation

    np_acts-logits-general · gemini-2.0-flash

    actions and states

    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
    Παραπομπές
    -0.41
    intios
    -0.38
     lo
    -0.37
     informée
    -0.37
     Pal
    -0.35
    tonode
    -0.34
     confided
    -0.32
    ABSTRACT
    -0.32
    Pal
    -0.32
    yr
    -0.32
    POSITIVE LOGITS
    SharedDtor
    0.66
     فريبيس
    0.65
     snippetHide
    0.63
    Personensuche
    0.56
    MigrationBuilder
    0.54
     disambiguazione
    0.53
     FetchType
    0.52
    IContainer
    0.52
    TargetException
    0.51
     contextLoads
    0.50
    Activations Density 1.069%

    No Known Activations