© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 18-GEMMASCOPE-RES-16K
    11. 861
    Prev
    Next
    INDEX
    Explanations

    terms related to false responses or incorrect answers in various contexts

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

    Non-English language fragments

    np_acts-logits-general · gemini-2.0-flash

    Romance and Slavic language word endings

    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
     purpoſe
    -1.17
     itſelf
    -1.15
     himſelf
    -1.06
     iſt
    -1.06
     myſelf
    -1.05
     Monfieur
    -1.03
     houſe
    -1.03
     Efq
    -1.01
     raiſ
    -1.01
     ſtate
    -1.00
    POSITIVE LOGITS
     ones
    0.65
     которые
    0.54
     
    0.51
     fantasies
    0.49
     b
    0.49
    Kanpo
    0.45
     d
    0.44
    vode
    0.43
     von
    0.43
     k
    0.43
    Activations Density 0.019%

    No Known Activations