© 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. 3083
    Prev
    Next
    INDEX
    Explanations

    terms related to situations and circumstances, particularly those with specific details

    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
     partid
    -0.68
     ejes
    -0.55
     bersih
    -0.55
    ormous
    -0.55
     conva
    -0.54
    veta
    -0.54
    maken
    -0.53
    SPARENT
    -0.53
     voisins
    -0.52
     élo
    -0.52
    POSITIVE LOGITS
     circumstances
    1.43
     situations
    1.42
     Situations
    1.29
     situation
    1.27
     conditions
    1.24
     circumstance
    1.23
    situation
    1.22
     Circumstances
    1.22
    Situation
    1.15
    conditions
    1.08
    Activations Density 0.379%

    No Known Activations