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. 4772
    Prev
    Next
    INDEX
    Explanations

    commands related to processes waiting for conditions to be met or actions to be completed

    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
    tadır
    -0.57
     Effort
    -0.54
    manship
    -0.53
    PyExc
    -0.49
    downe
    -0.44
     conservé
    -0.43
    Effort
    -0.43
    classnames
    -0.43
     riuscito
    -0.43
     actionBar
    -0.42
    POSITIVE LOGITS
    +#+#
    0.83
    makeConstraints
    0.68
    UnsafeEnabled
    0.64
    SpringBootTest
    0.64
    engertian
    0.63
    ViewFeatures
    0.62
     فريبيس
    0.62
    ersdorf
    0.61
     Normdatei
    0.61
    IUrlHelper
    0.60
    Activations Density 0.284%

    No Known Activations