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. 21-GEMMASCOPE-RES-16K
    6. 7014
    Prev
    Next
    INDEX
    Explanations

    conditional phrases and statements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 21-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_21/width_16k/average_l0_70
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.hook_resid_post
    Hook Layer
    21
    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
    -0.66
     Biôgrafia
    -0.64
    RTEE
    -0.64
     estekak
    -0.62
     IBOutlet
    -0.61
     bientôt
    -0.59
    StoryboardSegue
    -0.57
     évidence
    -0.55
    IBOutlet
    -0.55
     confiscation
    -0.53
    POSITIVE LOGITS
     you
    1.08
     we
    1.07
     they
    1.07
     there
    1.06
     someone
    0.84
     it
    0.76
     using
    0.72
     no
    0.71
     the
    0.71
     viewed
    0.70
    Activations Density 0.338%

    No Known Activations