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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 3975
    Prev
    Next
    INDEX
    Explanations

    references to educational content and course materials

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

    Academic course components: "lecture", "lab", etc

    np_acts-logits-general · gemini-2.0-flash

    course, lecture, class

    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
    ρεσ
    -0.47
    saraba
    -0.47
    afficheront
    -0.46
     ESQ
    -0.46
    edoria
    -0.45
    calciatore
    -0.45
     internally
    -0.45
     goda
    -0.45
    onBackPressed
    -0.45
     juvenile
    -0.45
    POSITIVE LOGITS
     lecture
    1.04
     lectures
    1.03
     instructor
    0.97
     Lecture
    0.97
     Lectures
    0.96
    lecture
    0.92
     class
    0.92
    Lecture
    0.91
     lecturer
    0.88
    Lectures
    0.86
    Activations Density 0.148%

    No Known Activations