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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 15-GEMMASCOPE-RES-16K
    11. 4642
    Prev
    Next
    INDEX
    Explanations

    specific nouns and entities related to businesses, programming, and data classification

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 15-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_15/width_16k/average_l0_131
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.15.hook_resid_post
    Hook Layer
    15
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     poveznice
    -0.35
     flavoured
    -0.33
     AUSSI
    -0.32
     conoci
    -0.32
    ฉ
    -0.32
    polarized
    -0.31
     polarized
    -0.31
    Founded
    -0.31
     querr
    -0.30
    뀜
    -0.30
    POSITIVE LOGITS
    +#+#
    0.59
    AccessorTable
    0.58
    AddTagHelper
    0.55
    jmniej
    0.54
     CreateTagHelper
    0.54
    elemField
    0.54
    存于互联网档案馆
    0.54
    IsMutable
    0.52
    CloseOperation
    0.50
     HasFactory
    0.50
    Activations Density 0.966%

    No Known Activations