Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 20-GEMMASCOPE-RES-16K
    6. 5192
    Prev
    Next
    INDEX
    Explanations

    questions that seek clarification or challenge assumptions

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

    Follows conjunctions/relative pronouns

    np_acts-logits-general · gemini-2.0-flash

    actions after clauses

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    AndEndTag
    -0.69
     використову
    -0.67
     calendriers
    -0.62
    UserScript
    -0.56
    bbene
    -0.55
     المعيارى
    -0.54
    Према
    -0.52
     Далее
    -0.49
     iconFacebook
    -0.47
    tende
    -0.47
    POSITIVE LOGITS
     having
    1.46
     getting
    1.39
    having
    1.25
     putting
    1.24
     taking
    1.23
     adding
    1.23
     doing
    1.21
     making
    1.18
     keeping
    1.17
     finding
    1.14
    Activations Density 1.025%

    No Known Activations