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. 14832
    Prev
    Next
    INDEX
    Explanations

    evidence and indications of relationships or outcomes

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

    Followed by "that."

    np_acts-logits-general · gemini-2.0-flash

    indicate or suggest something

    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
    每一次
    -0.53
     maxHeight
    -0.51
     cough
    -0.51
    OOTDTY
    -0.50
    credited
    -0.50
     Volga
    -0.49
     Macromolecules
    -0.49
     endfor
    -0.49
     deleteAll
    -0.49
     MacArthur
    -0.49
    POSITIVE LOGITS
    それだけ
    0.91
     either
    0.82
    Either
    0.80
     Either
    0.78
    webElementXpaths
    0.76
     serious
    0.74
    cheinend
    0.72
     demek
    0.71
    either
    0.71
    tagHelperRunner
    0.70
    Activations Density 0.429%

    No Known Activations