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-2-9B-IT
    4. Residual Stream - 16k
    5. 9-GEMMASCOPE-RES-16K
    6. 6867
    Prev
    Next
    INDEX
    Explanations

    phrases or terms that relate to opportunities and assessments of past actions or decisions

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

    "One of the" or similar phrases

    np_acts-logits-general · gemini-2.0-flash

    one of

    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
    matchCondition
    -0.63
    énario
    -0.61
    AndEndTag
    -0.58
     Theſe
    -0.58
    ChildScrollView
    -0.58
    PreExecute
    -0.58
    তথ্যসূত্র
    -0.57
     ***!
    -0.57
    OCCURRED
    -0.57
    ChromeDriver
    -0.56
    POSITIVE LOGITS
     egyik
    0.50
    之一
    0.48
     أحد
    0.45
     إحدى
    0.39
    gelopen
    0.34
    Kilder
    0.32
     geleden
    0.31
     another
    0.31
     salah
    0.31
    の一つ
    0.30
    Activations Density 0.516%

    No Known Activations