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 - 131k
    5. 9-GEMMASCOPE-RES-131K
    6. 25087
    Prev
    Next
    INDEX
    Explanations

    the definite article "the" in various contexts within the text

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

    the empire, prophet, slaves, cell, city, local

    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-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_9/width_131k/average_l0_121
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    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
     místě
    -0.42
     ringan
    -0.41
    tryk
    -0.41
     leçons
    -0.40
     deberes
    -0.40
     Evangelio
    -0.39
     duide
    -0.39
     sederhana
    -0.39
    leistungen
    -0.38
     laatste
    -0.38
    POSITIVE LOGITS
    ########.
    0.79
    oneofs
    0.63
    AddTagHelper
    0.61
    出版年
    0.60
    DIPSETTING
    0.59
    :+:
    0.57
    WriteTagHelper
    0.56
     ब्रेकडाउन
    0.54
    RectangleBorder
    0.54
    fileID
    0.54
    Activations Density 0.149%

    No Known Activations