© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 20-GEMMASCOPE-RES-16K
    11. 15222
    Prev
    Next
    INDEX
    Explanations

    references to problem-solving and challenges

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

    "problem" or "problems"

    np_acts-logits-general · gemini-2.0-flash

    problem solving formulation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    AnchorStyles
    -0.75
    AndEndTag
    -0.68
     gynhyrchwyd
    -0.67
    MLLoader
    -0.65
     itemprop
    -0.62
    jména
    -0.59
    stuffs
    -0.56
     popolare
    -0.56
     chrétienne
    -0.55
     aveug
    -0.55
    POSITIVE LOGITS
     problems
    1.39
     Problems
    1.38
     Problem
    1.34
     solved
    1.29
     solving
    1.27
     problem
    1.26
    Problems
    1.26
     PROBLEM
    1.23
    PROBLEM
    1.22
    Problem
    1.17
    Activations Density 0.066%

    No Known Activations