© 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
    4. Residual Stream - 16k
    5. 23-GEMMASCOPE-RES-16K
    6. 8894
    Prev
    Next
    INDEX
    Explanations

    mathematical expressions and variables

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 23-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_23/width_16k/average_l0_120
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.23.hook_resid_post
    Hook Layer
    23
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Gegenteil
    -0.44
    🦵
    -0.37
     fleuve
    -0.37
    reportWebVitals
    -0.35
     reverse
    -0.35
     AUTHORITY
    -0.32
    reverse
    -0.32
    gridad
    -0.31
     pilotes
    -0.31
    ⎝
    -0.30
    POSITIVE LOGITS
    WaitGroup
    0.68
    tagHelperRunner
    0.66
     disambiguazione
    0.65
     يتيمه
    0.63
    GOTREF
    0.62
    
    0.61
     tillegg
    0.61
    VIAF
    0.60
    脚注の使い方
    0.59
    IntoConstraints
    0.56
    Activations Density 2.049%

    No Known Activations