© 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. 22-GEMMASCOPE-RES-16K
    11. 285
    Prev
    Next
    INDEX
    Explanations

    phrases relating to material properties and their functionalities

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

    Ability or process of retaining/redirecting something (“to”, “which”)

    np_acts-logits-general · gemini-2.0-flash

    to funnel, absorb, retain

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 22-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_22/width_16k/average_l0_72
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.hook_resid_post
    Hook Layer
    22
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     éto
    -0.55
     faltar
    -0.53
     manca
    -0.50
     campaigning
    -0.46
     planification
    -0.45
     sauvages
    -0.45
    Недо
    -0.45
     mixte
    -0.45
     apparaître
    -0.44
    sunter
    -0.43
    POSITIVE LOGITS
     absorb
    1.20
     absorbing
    1.16
     absorbs
    1.16
     Absorb
    0.97
    absorb
    0.96
     Absor
    0.93
    absorbing
    0.91
     absor
    0.91
     trapping
    0.89
     trap
    0.89
    Activations Density 0.537%

    No Known Activations