© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 12-GEMMASCOPE-RES-16K
    6. 6880
    Prev
    Next
    INDEX
    Explanations

    specific structural or relationship terms in scientific contexts, often indicating research findings or methodology

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 12-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_12/width_16k/average_l0_130
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.hook_resid_post
    Hook Layer
    12
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     pleaſure
    -0.70
     myſelf
    -0.63
    Hentet
    -0.63
     faſt
    -0.63
     '\\;'
    -0.63
     كومونز
    -0.62
     ſche
    -0.62
     preſent
    -0.60
     ſur
    -0.59
     ſmall
    -0.58
    POSITIVE LOGITS
    /**
    0.47
     soñar
    0.40
    //
    0.37
    StoreMessageInfo
    0.36
    envolvimento
    0.35
    wußt
    0.35
     Papp
    0.34
    deviantart
    0.34
    SourceChecksum
    0.32
    ificato
    0.31
    Activations Density 1.766%

    No Known Activations