Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 0-GEMMASCOPE-RES-16K
    6. 7909
    Prev
    Next
    INDEX
    Explanations

    logical operators used in programming or mathematical expressions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 0-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_0/width_16k/average_l0_105
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.hook_resid_post
    Hook Layer
    0
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    o
    -0.73
    a
    -0.72
    e
    -0.67
    en
    -0.66
    i
    -0.66
    y
    -0.63
    p
    -0.62
    er
    -0.59
    ele
    -0.58
    b
    -0.58
    POSITIVE LOGITS
     Efq
    1.22
     Jefus
    1.21
     Chriftian
    1.20
     Houſe
    1.16
    )&&
    1.15
     Majefty
    1.14
     pleaſure
    1.11
     Eſ
    1.09
    setupUi
    1.08
     Diſ
    1.06
    Activations Density 0.298%

    No Known Activations