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

    Neuronpedia

    APICircuit 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. 16-GEMMASCOPE-RES-16K
    6. 12852
    Prev
    Next
    INDEX
    Explanations

    terms related to various forms of cryptography and advanced semiconductor devices

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

    Tokens appearing before parentheses or brackets

    np_acts-logits-general · gemini-2.0-flash

    conjunctions followed by list items

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 16-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_16/width_16k/average_l0_78
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.16.hook_resid_post
    Hook Layer
    16
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     comigo
    -0.58
     desconhe
    -0.54
     quelque
    -0.50
     pinulongan
    -0.49
    Демографія
    -0.47
     descansar
    -0.47
     esportivo
    -0.47
     destes
    -0.47
    Vanjske
    -0.45
     passengers
    -0.44
    POSITIVE LOGITS
     etc
    0.89
    最快更新
    0.78
    .")]
    0.75
    いわゆる
    0.73
    .}(
    0.72
     "];
    0.71
    ]<<"
    0.71
     ?>/
    0.71
    ----</
    0.71
     betweenstory
    0.70
    Activations Density 0.707%

    No Known Activations