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. 10-GEMMASCOPE-RES-16K
    6. 13286
    Prev
    Next
    INDEX
    Explanations

    references to different categories or types of items

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 10-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_10/width_16k/average_l0_77
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.10.hook_resid_post
    Hook Layer
    10
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     it
    -0.64
    k
    -0.63
    I
    -0.62
    1
    -0.56
    ck
    -0.56
    lid
    -0.55
    '
    -0.55
    id
    -0.54
    infeld
    -0.54
    It
    -0.54
    POSITIVE LOGITS
     various
    1.43
    various
    1.42
     sundry
    1.30
     Various
    1.28
    Various
    1.28
     assorted
    1.24
     VARIOUS
    1.20
     kinds
    1.20
     verschiedener
    1.16
     numerous
    1.15
    Activations Density 0.076%

    No Known Activations