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. 13-GEMMASCOPE-RES-16K
    6. 650
    Prev
    Next
    INDEX
    Explanations

    phrases indicating a basis for reasoning or conclusions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 13-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_13/width_16k/average_l0_84
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.13.hook_resid_post
    Hook Layer
    13
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ⓧ
    -0.74
    TagHelper
    -0.61
     accesorios
    -0.60
    bravo
    -0.59
     MonoBehaviour
    -0.56
     utafitiHapana
    -0.56
    JvmStatic
    -0.55
     acessórios
    -0.54
    Tikang
    -0.53
    archiviato
    -0.52
    POSITIVE LOGITS
    Based
    0.72
     beruht
    0.71
     Based
    0.69
    ">/
    0.68
    BASED
    0.67
    dasarkan
    0.67
     tiré
    0.67
    基于
    0.66
    に基
    0.65
     based
    0.64
    Activations Density 0.358%

    No Known Activations