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. 1-GEMMASCOPE-RES-16K
    6. 9371
    Prev
    Next
    INDEX
    Explanations

    references to educational curricula and related content

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 1-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_1/width_16k/average_l0_102
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.1.hook_resid_post
    Hook Layer
    1
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ագրություններ
    -0.68
    phorus
    -0.67
    photobucket
    -0.65
     defaultstate
    -0.63
    grao
    -0.60
    meldet
    -0.59
    modelBuilder
    -0.56
    Przypisy
    -0.56
    İstinadlar
    -0.54
     dead
    -0.54
    POSITIVE LOGITS
     curriculum
    1.24
     Curriculum
    1.17
    curriculum
    1.14
    Curriculum
    1.08
     curricula
    1.06
    RICULUM
    0.91
     kurikulum
    0.84
     curricular
    0.73
    courses
    0.67
     syllabus
    0.65
    Activations Density 0.065%

    No Known Activations