© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 18-GEMMASCOPE-RES-16K
    6. 14777
    Prev
    Next
    INDEX
    Explanations

    molecules and pathways related to cell metabolism and immune response

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

    before or related to receptors/inhibitors/agonists

    np_acts-logits-general · gemini-2.0-flash

    drug effects on biological components

    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
     Jefus
    -0.69
     ſeveral
    -0.63
    Tembelea
    -0.61
     occaf
    -0.59
    WriteTagHelper
    -0.59
     Monfieur
    -0.58
    RegistryLite
    -0.57
     Insee
    -0.57
     soaked
    -0.56
    💼
    -0.56
    POSITIVE LOGITS
     dysfunction
    0.58
     responsáveis
    0.56
     odpowiedzial
    0.55
    XmlAccessType
    0.55
    Referanser
    0.54
     responsável
    0.54
     műkö
    0.54
     responsible
    0.51
    fromnode
    0.51
     Dysfunction
    0.51
    Activations Density 1.267%

    No Known Activations