© 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. 24-GEMMASCOPE-RES-16K
    11. 15865
    Prev
    Next
    INDEX
    Explanations

    technical terms and specifications related to research and software development

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

    Code, names, or abbreviations followed by specific punctuation

    np_acts-logits-general · gemini-2.0-flash

    pro re nata, Semper Fi, Backing Filesystem

    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
    parsedMessage
    -0.59
     calendriers
    -0.58
    MLLoader
    -0.55
     GenerationType
    -0.55
    onAttach
    -0.55
     ProtoMessage
    -0.55
    GeneratedCode
    -0.53
     المعيارى
    -0.53
    Xna
    -0.53
    AnchorTagHelper
    -0.50
    POSITIVE LOGITS
    ymce
    0.61
     males
    0.61
     Aene
    0.59
     eu
    0.58
     Phase
    0.57
    Phase
    0.57
     phase
    0.57
     pell
    0.56
     tort
    0.55
     eget
    0.54
    Activations Density 0.086%

    No Known Activations