© 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. 2092
    Prev
    Next
    INDEX
    Explanations

    keywords related to programming structures and methods within object-oriented code

    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
    +#+
    -0.54
    évaluateur
    -0.50
    contentLoaded
    -0.46
    Diweddarwch
    -0.44
    点此举报
    -0.42
    kloped
    -0.42
    MLLoader
    -0.42
     pageContext
    -0.40
     utafitiHapana
    -0.39
     ContentValues
    -0.38
    POSITIVE LOGITS
    цездатний
    0.52
    createCanvas
    0.45
     ancestral
    0.44
    WebServlet
    0.43
    InputTagHelper
    0.43
     Tame
    0.42
    Usual
    0.42
    uero
    0.42
     Merv
    0.42
     Tristan
    0.41
    Activations Density 0.129%

    No Known Activations