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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    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. 2415
    Prev
    Next
    INDEX
    Explanations

    terms related to materials and their properties, particularly in a scientific context

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

    "higher" or comparative statements

    np_acts-logits-general · gemini-2.0-flash

    higher

    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
    TagMode
    -0.95
    tdessen
    -0.81
     saites
    -0.77
    Portail
    -0.77
    ImageContext
    -0.77
     MainAxisSize
    -0.75
    findpost
    -0.75
    FormTagHelper
    -0.71
     onCreateView
    -0.71
    UserScript
    -0.71
    POSITIVE LOGITS
     higher
    0.97
    higher
    0.77
     if
    0.76
    越
    0.75
    Higher
    0.73
     càng
    0.72
     Higher
    0.71
    越是
    0.71
     HIGHER
    0.70
     shorter
    0.69
    Activations Density 0.627%

    No Known Activations