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. 5953
    Prev
    Next
    INDEX
    Explanations

    elements related to cellular or anatomical structures, particularly within the nervous system and immune cells

    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
     Pingback
    -0.59
    __*/
    -0.54
    roek
    -0.51
     pinulongan
    -0.49
    neider
    -0.48
    testng
    -0.48
     compareTo
    -0.47
    StringTo
    -0.44
    telse
    -0.43
    ">#
    -0.42
    POSITIVE LOGITS
    findpost
    0.70
    ums
    0.60
    IUM
    0.58
    iferous
    0.57
    iform
    0.57
    um
    0.57
    ium
    0.54
    vician
    0.53
    scope
    0.52
    GenerationType
    0.51
    Activations Density 0.802%

    No Known Activations