© 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. 2872
    Prev
    Next
    INDEX
    Explanations

    references to solving complex mathematical problems

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

    preceding or related to "problem"

    np_acts-logits-general · gemini-2.0-flash

    solving problems

    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
    CodeAttribute
    -0.60
    Переваги
    -0.58
    impulan
    -0.53
    ucap
    -0.53
    牺牲
    -0.51
    ürger
    -0.50
     sacrifices
    -0.49
    Reagent
    -0.48
    Nazionale
    -0.48
     compensate
    -0.48
    POSITIVE LOGITS
     problem
    1.95
    problem
    1.74
     problems
    1.70
    Problem
    1.68
     Problem
    1.65
     problema
    1.53
     problème
    1.52
    problems
    1.51
     PROBLEM
    1.49
     Problems
    1.49
    Activations Density 0.613%

    No Known Activations