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. 406
    Prev
    Next
    INDEX
    Explanations

    details regarding experimental design and methodology in research studies

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

    "Per" or "each" followed by a unit or category

    np_acts-logits-general · gemini-2.0-flash

    items per group

    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
    ValueStyle
    -0.75
     विश्वसनीयता
    -0.66
    Xna
    -0.65
    StackNavigator
    -0.63
     <=",
    -0.62
    awakeFromNib
    -0.61
    ThemeOverlay
    -0.58
     للمعارف
    -0.58
     -->>
    -0.56
     intStringLen
    -0.54
    POSITIVE LOGITS
     each
    3.65
    each
    3.05
    Each
    2.91
     Each
    2.86
     EACH
    2.59
    EACH
    2.39
     chaque
    2.33
     chacun
    2.21
     chacune
    2.16
     fiecare
    2.14
    Activations Density 1.178%

    No Known Activations