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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 5-GEMMASCOPE-RES-16K
    11. 12449
    Prev
    Next
    INDEX
    Explanations

    phrases that include the expression "as far as" followed by a statement or idea

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.5.hook_resid_post
    Hook Layer
    5
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    UnusedPrivate
    -0.70
     OMIT
    -0.65
    CAPTION
    -0.60
     Vare
    -0.59
    VIAF
    -0.58
    postmedia
    -0.58
    Nonetheless
    -0.57
     transfieras
    -0.56
     fieldNum
    -0.56
    withstanding
    -0.56
    POSITIVE LOGITS
    coltà
    0.66
    zzleHttp
    0.63
    styleUrls
    0.60
    appBar
    0.60
    wapV
    0.59
     المعيارى
    0.58
    wanne
    0.58
     AppBar
    0.57
    oweit
    0.57
     StatusCode
    0.56
    Activations Density 0.071%

    No Known Activations