© 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. 10169
    Prev
    Next
    INDEX
    Explanations

    proper nouns and specific names related to various fields

    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
    UnusedPrivate
    -0.88
     kasarigan
    -0.66
    Kariera
    -0.65
    a
    -0.61
     برانيه
    -0.60
    Gator
    -0.59
    뢰
    -0.58
     høre
    -0.58
    på
    -0.57
    edale
    -0.57
    POSITIVE LOGITS
     JAM
    1.10
    mers
    1.08
     Erm
    1.07
    HAM
    1.05
     JIM
    1.04
     Dm
    1.02
     DPM
    1.01
     Bm
    1.00
     HEM
    0.99
     Hame
    0.99
    Activations Density 2.611%

    No Known Activations