© 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. 18-GEMMASCOPE-RES-16K
    11. 10944
    Prev
    Next
    INDEX
    Explanations

    phrases related to recognition or familiarity

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Preceding "known" or "know"

    np_acts-logits-general · gemini-2.0-flash

    phrases with 'known'

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.hook_resid_post
    Hook Layer
    18
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    favicon
    -0.58
    tagHelperRunner
    -0.57
    RenderAtEndOf
    -0.55
    Personensuche
    -0.55
    DotNetBar
    -0.52
     Puy
    -0.50
     Niem
    -0.49
     <<<<<<<<<<<<<<
    -0.48
     Dhabi
    -0.48
     Fergus
    -0.47
    POSITIVE LOGITS
    __':
    0.80
    Know
    0.79
    RetentionPolicy
    0.79
    จัก
    0.78
    ledge
    0.76
    KNOW
    0.74
     unknowns
    0.74
    know
    0.73
     Know
    0.73
    AsUp
    0.71
    Activations Density 0.148%

    No Known Activations