© 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-2-2B
    7. Residual Stream - 16k
    9. 5-GEMMASCOPE-RES-16K
    11. 15404
    Prev
    Next
    INDEX
    Explanations

    phrases that indicate services or offerings related to customer assistance

    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
     CreateTagHelper
    -0.85
    CloseOperation
    -0.82
     bezeichneter
    -0.82
    PhysRev
    -0.76
     ModelExpression
    -0.76
     ویکی‌پدیای
    -0.75
    ApiModelProperty
    -0.75
     HasFactory
    -0.73
    دانشنامهٔ
    -0.73
    kloped
    -0.72
    POSITIVE LOGITS
     We
    0.60
    We
    0.52
     our
    0.50
     offers
    0.49
    нах
    0.46
    Our
    0.45
     ldc
    0.43
     Our
    0.43
     provide
    0.43
     specialists
    0.43
    Activations Density 0.228%

    No Known Activations