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. 20-GEMMASCOPE-RES-16K
    6. 1109
    Prev
    Next
    INDEX
    Explanations

    references to research studies and their results

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

    [[@...]] citations

    np_acts-logits-general · gemini-2.0-flash

    citations and subsequent conjunctions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_16k/average_l0_91
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    httphttps
    -1.14
    ंदीखरीदारी
    -1.11
    RenderAtEndOf
    -1.10
    ьаж
    -1.09
    хьтан
    -1.08
    TagMode
    -1.07
     ویکی‌پدی
    -1.05
     noDo
    -1.05
    IsMutable
    -1.05
     otomatig
    -0.98
    POSITIVE LOGITS
    2
    0.39
    1
    0.35
    ).
    0.34
    8
    0.32
    ].
    0.32
    The
    0.32
    .
    0.30
    9
    0.30
     
    0.30
    ,
    0.29
    Activations Density 1.097%

    No Known Activations