© 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. 3477
    Prev
    Next
    INDEX
    Explanations

    code syntax elements related to object-oriented programming and data structure definitions

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

    Code, equations, or unusual capitalization

    np_acts-logits-general · gemini-2.0-flash

    file paths and system names

    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
    <eos>
    -1.01
    ↵
    -0.99
    1
    -0.84
    ↵↵
    -0.82
      
    -0.81
    2
    -0.81
    3
    -0.81
    ...
    -0.81
    '
    -0.79
    T
    -0.76
    POSITIVE LOGITS
     myſelf
    1.69
     itſelf
    1.61
     Efq
    1.51
    ^(@)
    1.47
     betweenstory
    1.40
     Theſe
    1.37
     Monfieur
    1.34
    BibitemShut
    1.31
     Jefus
    1.30
    __':
    1.30
    Activations Density 0.102%

    No Known Activations