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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 21-GEMMASCOPE-RES-16K
    6. 15485
    Prev
    Next
    INDEX
    Explanations

    different types of quotation marks and apostrophes used in text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 21-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_21/width_16k/average_l0_129
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.hook_resid_post
    Hook Layer
    21
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    AnchorTagHelper
    -0.47
     Calculator
    -0.46
     genomen
    -0.45
     loginUser
    -0.45
    GOTREF
    -0.44
    ukone
    -0.44
    loginUser
    -0.43
     समीक्षाएं
    -0.42
     startIndex
    -0.42
    edenken
    -0.42
    POSITIVE LOGITS
     ‘
    1.03
    “
    0.92
     ‘‘
    0.90
    (‘
    0.89
     “
    0.87
    ‘
    0.85
     (‘
    0.84
     '
    0.84
    =’
    0.82
    ‘‘
    0.80
    Activations Density 0.281%

    No Known Activations