© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    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. 11451
    Prev
    Next
    INDEX
    Explanations

    code-related elements, particularly those involving request handling and cookie management

    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
    rungsseite
    -0.90
    GEBURTSDATUM
    -0.85
     ویکی‌پدی
    -0.81
    RegressionTest
    -0.80
     Chwiliwch
    -0.80
    SourceChecksum
    -0.76
    下载附件
    -0.76
    transQ
    -0.76
    VIAF
    -0.69
    MessageOf
    -0.69
    POSITIVE LOGITS
    flashdata
    0.61
    DataAnnotations
    0.59
    ">@
    0.54
     his
    0.52
     IBOutlet
    0.52
    viewDid
    0.50
     Савезне
    0.50
    demic
    0.49
    UIControlState
    0.49
    BagConstraints
    0.49
    Activations Density 0.022%

    No Known Activations