© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 18-GEMMASCOPE-RES-16K
    11. 6730
    Prev
    Next
    INDEX
    Explanations

    references to legal citations and case numbers

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

    Citations to court cases

    np_acts-logits-general · gemini-2.0-flash

    legal citations

    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
    äsident
    -0.53
    ufige
    -0.49
    ElementException
    -0.48
    Bust
    -0.48
    Diweddarwch
    -0.47
    клопе
    -0.47
     Blit
    -0.47
     chopsticks
    -0.46
     sociétés
    -0.46
     reckoned
    -0.46
    POSITIVE LOGITS
    AutoField
    0.73
     déploy
    0.62
     wireType
    0.55
    DrawerToggle
    0.52
    Parcelize
    0.52
    Honours
    0.51
    SOUNDBITE
    0.50
    WriteLiteral
    0.49
    requestCode
    0.48
    FundMe
    0.47
    Activations Density 0.138%

    No Known Activations