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-2-2B
    4. Residual Stream - 16k
    5. 7-GEMMASCOPE-RES-16K
    6. 6347
    Prev
    Next
    INDEX
    Explanations

    technical terms and symbols related to programming or coding

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 7-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_7/width_16k/average_l0_69
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.7.hook_resid_post
    Hook Layer
    7
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    textTheme
    -0.60
    PageRoute
    -0.60
    ReusableCell
    -0.60
    AutoField
    -0.59
    Personendaten
    -0.59
     '\\;'
    -0.57
    latego
    -0.53
     viewDidLoad
    -0.52
     utafitiHapana
    -0.52
     nargin
    -0.52
    POSITIVE LOGITS
     Theſe
    0.69
    وأضاف
    0.68
    queryInterface
    0.64
     thác
    0.58
    Chham
    0.58
    Merken
    0.56
    σμο
    0.56
    zysz
    0.55
    łożyć
    0.54
    обходимо
    0.54
    Activations Density 0.383%

    No Known Activations