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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 14-GEMMASCOPE-RES-16K
    6. 4043
    Prev
    Next
    INDEX
    Explanations

    concepts related to misconceptions and fallacies in reasoning

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 14-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_14/width_16k/average_l0_84
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.14.hook_resid_post
    Hook Layer
    14
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     purpoſe
    -0.77
     متعلقه
    -0.76
    Diwedd
    -0.73
     houſe
    -0.72
     itſelf
    -0.69
    ſelf
    -0.68
     Jefus
    -0.67
     uſe
    -0.66
    حياتها
    -0.66
    ſelves
    -0.66
    POSITIVE LOGITS
     misunder
    0.59
     often
    0.59
     wrongly
    0.54
     wrong
    0.54
     ignor
    0.53
     Often
    0.53
     mistaken
    0.53
     misunderstand
    0.51
     sometimes
    0.50
     incorrect
    0.50
    Activations Density 0.454%

    No Known Activations