Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 20-GEMMASCOPE-RES-16K
    6. 1539
    Prev
    Next
    INDEX
    Explanations

    programming-related identifiers and definitions

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

    C preprocessor #define directives

    np_acts-logits-general · gemini-2.0-flash

    identifiers followed by underscore

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    gmail
    -0.64
    ٍ
    -0.47
    WriteBarrier
    -0.46
    ว
    -0.45
    DECREF
    -0.43
    <sup>
    -0.43
     $^{
    -0.42
    ̊
    -0.42
    ◆
    -0.41
    .,
    -0.41
    POSITIVE LOGITS
    _
    1.69
    \_
    1.16
    _%
    0.97
    _$
    0.97
     _
    0.95
    _{
    0.90
    _\
    0.90
    }_
    0.90
    _-_
    0.90
    _[
    0.89
    Activations Density 0.774%

    No Known Activations