© 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. 25-GEMMASCOPE-RES-16K
    6. 15063
    Prev
    Next
    INDEX
    Explanations

    function calls related to memory management and object handling

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 25-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_25/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.25.hook_resid_post
    Hook Layer
    25
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ϖ
    -0.43
    調
    -0.42
     auszu
    -0.42
     queſta
    -0.42
    忠
    -0.41
     EdgeInsets
    -0.41
    ラマ
    -0.41
    AndEndTag
    -0.40
     Wray
    -0.40
    copo
    -0.40
    POSITIVE LOGITS
    principalTable
    0.65
     estekak
    0.60
    yntaxException
    0.53
    ImageContext
    0.53
     proprement
    0.46
     HttpNotFound
    0.43
    GEBURTS
    0.42
    parsedMessage
    0.42
    drawiam
    0.40
     виправивши
    0.40
    Activations Density 0.103%

    No Known Activations