© 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. 911
    Prev
    Next
    INDEX
    Explanations

    terms related to challenges and solutions in research or technical fields

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

    Follows verbs like inspires, operate, or enabling

    np_acts-logits-general · gemini-2.0-flash

    promotional fundraising social programs

    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
     confronti
    -0.61
     CJK
    -0.61
     Shakspeare
    -0.58
     atheists
    -0.57
    RTEE
    -0.56
    IVEREF
    -0.56
     Efq
    -0.54
     fotografico
    -0.53
     bancaria
    -0.53
     EEU
    -0.53
    POSITIVE LOGITS
     marketing
    0.72
     promotional
    0.62
    RenderAtEndOf
    0.60
     public
    0.60
     coaching
    0.60
    PRNewswire
    0.58
     fundraising
    0.57
     social
    0.57
     programs
    0.56
     annual
    0.56
    Activations Density 1.214%

    No Known Activations