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

    Neuronpedia

    APIAssistant AxisNEWCircuit 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. 3439
    Prev
    Next
    INDEX
    Explanations

    instances of the word "Ver" in various contexts, likely related to versioning or verification concepts

    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
    kháu
    -0.56
    ⎞
    -0.55
    :]:
    -0.51
     المرجع
    -0.51
     Audiodateien
    -0.47
    Secondly
    -0.47
     propOrder
    -0.47
    ToBounds
    -0.46
    Gotcha
    -0.45
    utnik
    -0.45
    POSITIVE LOGITS
    ticals
    0.61
    ProgressHUD
    0.55
    tically
    0.55
    million
    0.54
    mouth
    0.52
    ticle
    0.51
    bena
    0.51
     pelicula
    0.49
     lèvres
    0.49
    bindings
    0.48
    Activations Density 0.184%

    No Known Activations