© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 8-GEMMASCOPE-RES-16K
    6. 15272
    Prev
    Next
    INDEX
    Explanations

    terms related to quality or ranking comparisons

    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
    an
    -1.03
    o
    -0.97
    er
    -0.95
    p
    -0.90
    k
    -0.90
    u
    -0.86
     k
    -0.85
    r
    -0.83
    a
    -0.83
    q
    -0.82
    POSITIVE LOGITS
     myſelf
    1.51
     greateſt
    1.50
     beſt
    1.48
     ་་
    1.41
     itſelf
    1.40
     iſt
    1.38
     leaſt
    1.37
     Majefty
    1.37
     firſt
    1.37
    ſelves
    1.33
    Activations Density 0.071%

    No Known Activations