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. 18-GEMMASCOPE-RES-16K
    6. 15059
    Prev
    Next
    INDEX
    Explanations

    references to font types and specifications

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

    "font" and related typography

    np_acts-logits-general · gemini-2.0-flash

    font properties and names

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.hook_resid_post
    Hook Layer
    18
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     EconPapers
    -0.78
    onViewCreated
    -0.70
     sortant
    -0.57
    moveToFirst
    -0.57
     malheure
    -0.55
     préciser
    -0.54
     paraître
    -0.54
    uminense
    -0.53
     alcun
    -0.53
    rull
    -0.53
    POSITIVE LOGITS
     FONT
    1.27
     font
    1.26
    font
    1.20
     Fonts
    1.18
     fonts
    1.17
     Font
    1.17
    fonts
    1.06
    Font
    1.00
     Fontana
    0.96
    Fonts
    0.91
    Activations Density 0.042%

    No Known Activations