© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 8-GEMMASCOPE-RES-16K
    11. 7948
    Prev
    Next
    INDEX
    Explanations

    references to educators and teaching professionals

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 8-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_8/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.8.hook_resid_post
    Hook Layer
    8
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Ĩ
    -0.88
    وذ
    -0.85
     Kini
    -0.81
    Rog
    -0.72
    AsyncResult
    -0.71
     ARISING
    -0.71
     XLV
    -0.70
    nders
    -0.69
    sS
    -0.67
     Sloane
    -0.66
    POSITIVE LOGITS
     teachers
    1.31
     Teachers
    1.20
     teacher
    1.17
    Teachers
    1.14
    teachers
    1.13
     Teacher
    1.12
    teacher
    1.08
     TEACHER
    1.06
    TEACHER
    1.06
    Teacher
    0.94
    Activations Density 0.047%

    No Known Activations