© 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. 6430
    Prev
    Next
    INDEX
    Explanations

    terms related to cognitive performance and assessment in clinical contexts

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

    tasks or task performance

    np_acts-logits-general · gemini-2.0-flash

    visual-motor tasks

    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
     flesh
    -0.55
    flesh
    -0.52
    Getenv
    -0.50
    JpaRepository
    -0.50
    __(/*!
    -0.49
    حوالہ
    -0.49
     poros
    -0.49
     demografica
    -0.48
    IRQn
    -0.48
    usermodel
    -0.48
    POSITIVE LOGITS
     coordon
    0.60
     TextInputType
    0.55
     coordination
    0.55
     StatelessWidget
    0.54
     الرياضيه
    0.54
     Tasks
    0.53
    complexType
    0.52
     tasks
    0.52
    enação
    0.51
     CreateTagHelper
    0.51
    Activations Density 0.354%

    No Known Activations