© 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. 3-GEMMASCOPE-RES-16K
    11. 3071
    Prev
    Next
    INDEX
    Explanations

    terms related to geographical locations and trails

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 3-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_3/width_16k/average_l0_59
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.hook_resid_post
    Hook Layer
    3
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Whilst
    -1.39
     Whilst
    -1.31
    initialise
    -1.30
     tyres
    -1.27
     recognisable
    -1.27
     organised
    -1.26
     enquiries
    -1.24
    centre
    -1.23
    Organiser
    -1.23
     organising
    -1.23
    POSITIVE LOGITS
     confiable
    1.28
    ônicos
    1.11
    Neighbors
    1.09
     neighbors
    1.07
     Neighbors
    1.06
     neighborhoods
    1.05
     favors
    1.05
     parlor
    1.04
     neighbor
    1.04
    ônico
    1.03
    Activations Density 3.658%

    No Known Activations