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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B-IT
    4. Residual Stream - 16k
    5. 9-GEMMASCOPE-RES-16K
    6. 3022
    Prev
    Next
    INDEX
    Explanations

    specific pronouns and demonstrative references

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Japanese "sore" (それ) and "kore" (これ)

    np_acts-logits-general · gemini-2.0-flash

    this or that

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 9-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-it-res/layer_9/width_16k/average_l0_88
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.9.hook_resid_post
    Hook Layer
    9
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     resourceCulture
    -0.76
    -------
    -0.73
     snippetHide
    -0.68
    ChildScrollView
    -0.66
     ویکی‌پدی
    -0.65
     OMITBAD
    -0.62
    providedIn
    -0.62
     Normdatei
    -0.60
     esternos
    -0.60
    ########.
    -0.59
    POSITIVE LOGITS
    これ
    0.63
     isso
    0.59
     Isso
    0.50
    这
    0.50
     Ciò
    0.49
    Isso
    0.48
     ciò
    0.48
     Đây
    0.47
     αυτό
    0.47
     itu
    0.46
    Activations Density 0.221%

    No Known Activations