© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 22-GEMMASCOPE-RES-16K
    6. 6398
    Prev
    Next
    INDEX
    Explanations

    technical terms and functions related to data structures and algorithms

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

    Code, data structures, and algorithms

    np_acts-logits-general · gemini-2.0-flash

    insertion and data structure operations

    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
     translating
    -0.44
    łyn
    -0.42
     quedarse
    -0.42
     abbre
    -0.41
    gelöst
    -0.41
     znam
    -0.41
    Contours
    -0.40
     cashback
    -0.40
     واب
    -0.40
    itados
    -0.39
    POSITIVE LOGITS
     Insertion
    1.04
     insertion
    1.03
     insert
    1.02
     Insert
    0.99
     INSERT
    0.97
     للمعارف
    0.94
    Insert
    0.94
    Insertion
    0.93
    Бахар
    0.91
     inserts
    0.90
    Activations Density 0.298%

    No Known Activations