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. 18-GEMMASCOPE-RES-16K
    6. 8592
    Prev
    Next
    INDEX
    Explanations

    terms related to scientific studies and findings

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

    "review" or "recent"

    np_acts-logits-general · gemini-2.0-flash

    recent review

    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
     لكرة
    -0.43
    Risultati
    -0.43
     gro
    -0.43
     fin
    -0.43
    msgTypes
    -0.42
    aki
    -0.41
    acos
    -0.41
     margin
    -0.41
    披
    -0.41
     je
    -0.40
    POSITIVE LOGITS
     reviews
    1.37
     review
    1.36
    review
    1.29
    Review
    1.23
     Review
    1.22
     reviewed
    1.20
     reviewing
    1.20
    reviews
    1.19
    reviewed
    1.18
     Reviews
    1.18
    Activations Density 0.914%

    No Known Activations