© 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-2-2B
    4. Residual Stream - 16k
    5. 16-GEMMASCOPE-RES-16K
    6. 2157
    Prev
    Next
    INDEX
    Explanations

    lines of code that define or reference generic data structures

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Code-related terms and generic names

    np_acts-logits-general · gemini-2.0-flash

    generic language or terms

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 16-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_16/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.16.hook_resid_post
    Hook Layer
    16
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    MessageTagHelper
    -0.65
    cifix
    -0.64
    DockStyle
    -0.63
    :✨
    -0.60
    mergeFrom
    -0.57
    fficio
    -0.56
    etcode
    -0.56
    Applies
    -0.54
    웠
    -0.53
    #
    -0.52
    POSITIVE LOGITS
    Generic
    1.05
     Generic
    0.68
    generic
    0.66
     Embar
    0.64
    Embar
    0.60
     generic
    0.59
    GENERIC
    0.57
    <tbody>
    0.56
    stddef
    0.56
    stdc
    0.55
    Activations Density 0.005%

    No Known Activations