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. 140
    Prev
    Next
    INDEX
    Explanations

    phrases related to the disclosure of information or statements

    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
    KommentareTeilen
    -0.53
     Google
    -0.52
     b
    -0.50
    Personendaten
    -0.48
    อก
    -0.48
    EDING
    -0.48
    otic
    -0.47
     #
    -0.46
     nok
    -0.46
     '
    -0.46
    POSITIVE LOGITS
    said
    1.23
    Said
    1.20
     stated
    1.09
     said
    1.03
     Said
    1.01
    ContentAsync
    0.98
     reported
    0.95
    stated
    0.91
     SAID
    0.89
    reported
    0.83
    Activations Density 0.203%

    No Known Activations