© 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. 4-GEMMASCOPE-RES-16K
    11. 885
    Prev
    Next
    INDEX
    Explanations

    medical terminology related to diagnostic procedures and treatments

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 4-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_4/width_16k/average_l0_124
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.hook_resid_post
    Hook Layer
    4
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    adaptiveStyles
    -0.61
    ỡng
    -0.56
     considérons
    -0.55
    IsContent
    -0.54
     protoimpl
    -0.53
    ConstraintMaker
    -0.53
    DockStyle
    -0.52
    findpost
    -0.51
    ngdoc
    -0.50
    wyl
    -0.50
    POSITIVE LOGITS
    Sprintf
    0.52
     мәкалә
    0.50
     betweenstory
    0.47
    ítása
    0.46
     internasional
    0.46
    ToLeft
    0.45
    ContentAlignment
    0.45
     pemerintah
    0.44
    rupulous
    0.43
    rekli
    0.43
    Activations Density 4.035%

    No Known Activations