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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 24-GEMMASCOPE-RES-16K
    6. 12711
    Prev
    Next
    INDEX
    Explanations

    programming and markup syntax elements

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

    Code-related punctuation and symbols

    np_acts-logits-general · gemini-2.0-flash

    code comments and blocks

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 24-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_24/width_16k/average_l0_73
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.hook_resid_post
    Hook Layer
    24
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    LEncoder
    -0.60
    IsContent
    -0.57
    Personendaten
    -0.55
    hoes
    -0.55
    IUrlHelper
    -0.53
    URLConnection
    -0.51
    weetened
    -0.51
    IndentedString
    -0.50
    djangoproject
    -0.50
    richTextPanel
    -0.50
    POSITIVE LOGITS
     <<<<<<<<<<<<<<
    0.62
    ..<
    0.53
    ?<
    0.49
    See
    0.49
    This
    0.48
     Abar
    0.48
     Protobuf
    0.47
    ாம்
    0.46
    >";
    0.46
     ">=
    0.46
    Activations Density 0.104%

    No Known Activations