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

    Neuronpedia

    APICircuit 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. 13776
    Prev
    Next
    INDEX
    Explanations

    elements related to data structures and memory management in programming

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

    Code snippets and abbreviations

    np_acts-logits-general · gemini-2.0-flash

    identifier member access notation

    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
     ban
    -0.48
     N
    -0.48
     good
    -0.47
     spo
    -0.46
     Ban
    -0.44
     a
    -0.44
     Small
    -0.44
     (
    -0.43
     Su
    -0.42
     or
    -0.42
    POSITIVE LOGITS
     صوتيه
    0.90
     Efq
    0.86
     purpoſe
    0.85
     poffible
    0.85
    nefs
    0.83
    ſelves
    0.81
     ་་
    0.80
     Majefty
    0.80
     reaſon
    0.79
     myſelf
    0.79
    Activations Density 0.104%

    No Known Activations