© 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-2-2B
    4. Residual Stream - 16k
    5. 15-GEMMASCOPE-RES-16K
    6. 5446
    Prev
    Next
    INDEX
    Explanations

    elements related to measurements and classifications in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 15-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_15/width_16k/average_l0_78
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.15.hook_resid_post
    Hook Layer
    15
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    WriteTagHelper
    -0.84
    Архівовано
    -0.82
     ExecuteAsync
    -0.78
    DebuggerStep
    -0.72
     مشين
    -0.72
    NUMX
    -0.69
    initComponents
    -0.66
     Réponses
    -0.66
    intios
    -0.66
     AssemblyVersion
    -0.65
    POSITIVE LOGITS
    ang
    0.56
    kes
    0.55
    fe
    0.52
    ano
    0.51
    ú
    0.51
    con
    0.51
    leg
    0.50
    ra
    0.49
    ere
    0.49
    ck
    0.49
    Activations Density 1.260%

    No Known Activations