© 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. 20-GEMMASCOPE-RES-16K
    11. 11308
    Prev
    Next
    INDEX
    Explanations

    references to individual people, particularly in a reporting context

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

    Attribution, followed by a quote

    np_acts-logits-general · gemini-2.0-flash

    subject speaks and is quoted

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    addCriterion
    -0.50
     насељу
    -0.47
    <bos>
    -0.46
    спользу
    -0.46
    getMenuInflater
    -0.46
    atória
    -0.44
     getClass
    -0.43
     isn
    -0.42
     zwar
    -0.42
    Ợ
    -0.42
    POSITIVE LOGITS
     said
    1.43
    said
    1.19
     Said
    1.07
    Said
    1.06
     says
    0.99
     SAID
    0.99
     stated
    0.97
     say
    0.89
     wrote
    0.88
     concluded
    0.83
    Activations Density 0.071%

    No Known Activations