© 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. 13754
    Prev
    Next
    INDEX
    Explanations

    specific athletes and related sports statistics or achievements

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

    Appears before/after names or titles

    np_acts-logits-general · gemini-2.0-flash

    names and titles

    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
    TypedDataSet
    -0.93
     autorytatywna
    -0.88
     <<<<<<<<<<<<<<
    -0.68
     disambiguazione
    -0.68
     Administrativna
    -0.67
    IndentedString
    -0.66
     noDo
    -0.65
    enumii
    -0.63
     linkovi
    -0.63
     AssemblyCulture
    -0.60
    POSITIVE LOGITS
     betweenstory
    0.38
     развер
    0.37
     Übergang
    0.35
     asmen
    0.35
     braccia
    0.35
     buzz
    0.35
    endroit
    0.34
     recently
    0.34
     tė
    0.33
     Deixe
    0.33
    Activations Density 0.379%

    No Known Activations