© 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. 14-GEMMASCOPE-RES-16K
    11. 9222
    Prev
    Next
    INDEX
    Explanations

    mathematical and scientific variables, equations, and their derivatives

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 14-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_14/width_16k/average_l0_67
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.14.hook_resid_post
    Hook Layer
    14
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     disambiguazione
    -0.67
    SequentialGroup
    -0.64
    PCell
    -0.62
    CppMethod
    -0.61
    established
    -0.56
     established
    -0.55
    interopRequire
    -0.53
     zwiſchen
    -0.53
    Hochspringen
    -0.52
    ernalia
    -0.52
    POSITIVE LOGITS
     otomatig
    0.41
     saites
    0.39
    المكان
    0.36
    SaveChangesAsync
    0.35
    DebuggerNonUser
    0.35
    Cyfeiriadau
    0.33
    ngOnInit
    0.32
    TypedDataSet
    0.31
    ScopeManager
    0.30
     arbete
    0.30
    Activations Density 0.758%

    No Known Activations