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. 14-GEMMASCOPE-RES-16K
    6. 3563
    Prev
    Next
    INDEX
    Explanations

    specialized terms and symbols related to scientific notation and materials

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 14-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_14/width_16k/average_l0_84
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.14.hook_resid_post
    Hook Layer
    14
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     catch
    -0.53
    ))^{
    -0.53
    +}$
    -0.47
    }}}{\
    -0.47
     Feld
    -0.46
    以
    -0.45
     di
    -0.44
    وقع
    -0.43
    }}^{
    -0.43
    {}",
    -0.43
    POSITIVE LOGITS
    migrationBuilder
    0.91
    DoubleQuotes
    0.80
    ագրություններ
    0.77
     '\\;'
    0.77
    فایل‌لار
    0.77
     saites
    0.76
    IUrlHelper
    0.75
    oredCriteria
    0.74
     مواليد
    0.72
    uxxxx
    0.71
    Activations Density 1.154%

    No Known Activations