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. 4-GEMMASCOPE-RES-16K
    6. 654
    Prev
    Next
    INDEX
    Explanations

    prepositions indicating location or position

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 4-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_4/width_16k/average_l0_124
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.hook_resid_post
    Hook Layer
    4
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     ―――――
    -1.07
     ་་
    -1.06
     Monfieur
    -1.01
     Anſ
    -0.97
     itſelf
    -0.96
     purpoſe
    -0.94
     Chriftian
    -0.93
     ſche
    -0.92
     Houſe
    -0.91
     raiſ
    -0.91
    POSITIVE LOGITS
     in
    1.86
     In
    1.42
     IN
    1.41
    In
    1.20
    in
    1.18
     в
    1.08
     isIn
    1.03
     în
    1.03
     في
    0.92
     dalam
    0.92
    Activations Density 1.066%

    No Known Activations