© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 18-GEMMASCOPE-RES-16K
    11. 15077
    Prev
    Next
    INDEX
    Explanations

    terms and phrases related to limitations or challenges in various contexts

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

    preceding "problem" or "issue"

    np_acts-logits-general · gemini-2.0-flash

    problem, issue, or concern

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.hook_resid_post
    Hook Layer
    18
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Hentet
    -0.76
     autorytatywna
    -0.70
    RefreshLayout
    -0.60
     nahilalakip
    -0.57
    
    -0.53
    posób
    -0.51
    ADELPHIA
    -0.51
    StoryboardSegue
    -0.50
    fastjson
    -0.50
    iritto
    -0.49
    POSITIVE LOGITS
     problem
    1.47
    problem
    1.38
     problema
    1.33
     problems
    1.32
     problème
    1.28
     issue
    1.27
    problems
    1.24
     PROBLEM
    1.20
     Problem
    1.18
    Problem
    1.17
    Activations Density 0.400%

    No Known Activations