© 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
    7. Residual Stream - 16k
    9. 33-GEMMASCOPE-RES-16K
    11. 8482
    Prev
    Next
    INDEX
    Explanations

    various types of configuration settings and their parameters

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 33-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_33/width_16k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.33.hook_resid_post
    Hook Layer
    33
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ThemeOverlay
    -0.42
    elemField
    -0.40
    OGND
    -0.40
    enido
    -0.37
    Zel
    -0.36
    ellido
    -0.35
     Италијани
    -0.35
    lapia
    -0.35
    ETHING
    -0.35
     tør
    -0.34
    POSITIVE LOGITS
     getConfig
    0.67
     Config
    0.67
    urator
    0.66
    urazione
    0.57
     cfg
    0.56
     settings
    0.56
    urate
    0.56
     config
    0.55
    urat
    0.53
     CONFIG
    0.52
    Activations Density 0.094%

    No Known Activations