© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 3-GEMMASCOPE-RES-16K
    11. 5887
    Prev
    Next
    INDEX
    Explanations

    specific phrases and terms related to mathematical operations or definitions, particularly those that involve sequences, functions, or parameters in structured formats

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 3-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_3/width_16k/average_l0_59
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.hook_resid_post
    Hook Layer
    3
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    MENAFN
    -0.52
    thro
    -0.52
    tymologie
    -0.50
     demas
    -0.48
    .(*
    -0.47
    TabIndex
    -0.46
     Bras
    -0.46
    مراجع
    -0.46
     J
    -0.46
     Perf
    -0.45
    POSITIVE LOGITS
     <<<<<<<<<<<<<<
    0.82
    IntoConstraints
    0.79
    aarrggbb
    0.78
     CreateTagHelper
    0.66
    EDEFAULT
    0.65
     autorytatywna
    0.64
    InSection
    0.64
    ✨:
    0.63
    setVerticalGroup
    0.63
     OFDb
    0.63
    Activations Density 0.331%

    No Known Activations