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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlogSlackPrivacy & 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. 1881
    Prev
    Next
    INDEX
    Explanations

    references to regional geography and natural landscapes

    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
    ########.
    -0.80
    CloseOperation
    -0.65
     AssemblyCompany
    -0.55
    EndProject
    -0.55
    \{\\
    -0.54
     autorytatywna
    -0.54
    ValueStyle
    -0.53
    Autoritní
    -0.53
    хьтан
    -0.51
     EconPapers
    -0.51
    POSITIVE LOGITS
     Seen
    0.61
    Seen
    0.59
     Strand
    0.56
     Boots
    0.54
     See
    0.53
     Sees
    0.52
     Wander
    0.51
    ocin
    0.50
    Boots
    0.49
    See
    0.49
    Activations Density 0.068%

    No Known Activations