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. 25-GEMMASCOPE-RES-16K
    6. 5924
    Prev
    Next
    INDEX
    Explanations

    verbs and forms of the verb "to be."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 25-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_25/width_16k/average_l0_116
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.hook_resid_post
    Hook Layer
    25
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ️
    -0.74
     Including
    -0.62
    RectangleBorder
    -0.60
     Containing
    -0.58
    these
    -0.56
    Including
    -0.56
    avec
    -0.54
    containing
    -0.54
     dass
    -0.53
    including
    -0.53
    POSITIVE LOGITS
     also
    1.29
     indeed
    1.20
     now
    1.20
     actually
    1.16
     not
    1.15
     usually
    1.15
     often
    1.14
     certainly
    1.12
     always
    1.06
     undoubtedly
    1.01
    Activations Density 1.625%

    No Known Activations