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. 5-GEMMASCOPE-RES-16K
    6. 1208
    Prev
    Next
    INDEX
    Explanations

    expressions of hope and encouragement for improvement or change

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.5.hook_resid_post
    Hook Layer
    5
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ftagPool
    -0.79
    MessageTagHelper
    -0.74
    providedIn
    -0.73
    󠁢
    -0.72
     كومونز
    -0.71
    fois
    -0.65
     PackageManager
    -0.64
    pellier
    -0.64
    LabelTagHelper
    -0.64
     المعيارى
    -0.64
    POSITIVE LOGITS
    webElementGuid
    0.49
    matchCondition
    0.47
    才行
    0.46
    assert
    0.44
    しないと
    0.44
    etal
    0.44
     dag
    0.41
    규
    0.41
     phải
    0.40
    infer
    0.40
    Activations Density 0.136%

    No Known Activations