© 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. 2947
    Prev
    Next
    INDEX
    Explanations

    HTML class attributes in the document

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

    `className` and related HTML/JSX attributes

    np_acts-logits-general · gemini-2.0-flash

    className='card'

    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
    jface
    -0.57
     Bland
    -0.53
     delantera
    -0.49
    a
    -0.48
    Bland
    -0.48
     kit
    -0.48
    การ
    -0.47
    lot
    -0.47
    gamon
    -0.46
     dép
    -0.46
    POSITIVE LOGITS
    Datuak
    0.96
    BeginContext
    0.95
     Efq
    0.92
     className
    0.88
     متعلقه
    0.88
     препратки
    0.87
    __*/
    0.87
     myſelf
    0.84
     Jefus
    0.82
    ReusableCell
    0.80
    Activations Density 0.008%

    No Known Activations