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. 16-GEMMASCOPE-RES-16K
    6. 15021
    Prev
    Next
    INDEX
    Explanations

    instances of names and proper nouns

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

    First name followed by a verb

    np_acts-logits-general · gemini-2.0-flash

    names followed by actions

    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
    tagHelperRunner
    -0.92
     AssemblyCulture
    -0.77
    帖最后由
    -0.69
     المعيارى
    -0.69
    +#+#
    -0.68
     propOrder
    -0.68
    :✨
    -0.67
     nahilalakip
    -0.67
    KommentareTeilen
    -0.65
    badlogic
    -0.63
    POSITIVE LOGITS
    ’
    0.77
     also
    0.76
    '
    0.70
     began
    0.60
     spent
    0.58
     started
    0.57
     همچنین
    0.56
     has
    0.52
     alfo
    0.52
     originally
    0.52
    Activations Density 0.285%

    No Known Activations