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. 22-GEMMASCOPE-RES-16K
    6. 12864
    Prev
    Next
    INDEX
    Explanations

    information related to educational qualifications and schooling

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

    Followed by "secondary" or "primary"

    np_acts-logits-general · gemini-2.0-flash

    primary and secondary schooling

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 22-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_22/width_16k/average_l0_72
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.hook_resid_post
    Hook Layer
    22
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    reactstrap
    -0.63
     kuliah
    -0.62
     كومونز
    -0.62
    IntoConstraints
    -0.61
     étudiants
    -0.60
    craper
    -0.60
     mahasiswa
    -0.58
     GenerationType
    -0.58
     étudiant
    -0.57
    ConstraintMaker
    -0.56
    POSITIVE LOGITS
     Secondary
    0.99
     secondary
    0.97
     Primary
    0.93
    Primary
    0.91
    Secondary
    0.91
    primary
    0.90
     primary
    0.90
     PRIMARY
    0.86
    secondary
    0.81
    PRIMARY
    0.78
    Activations Density 0.137%

    No Known Activations