© 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. 2609
    Prev
    Next
    INDEX
    Explanations

    references to articles and papers

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

    articles, papers, or manuscripts

    np_acts-logits-general · gemini-2.0-flash

    the article discusses

    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
     betweenstory
    -1.02
    oa̍t
    -1.01
     Administrativna
    -0.99
     дописавши
    -0.99
     ModelExpression
    -0.96
     فريبيس
    -0.91
    OGND
    -0.90
     hObject
    -0.90
     незавершена
    -0.90
    __*/
    -0.87
    POSITIVE LOGITS
     will
    0.55
     venido
    0.44
     set
    0.41
     was
    0.41
     belong
    0.41
     is
    0.41
     originally
    0.40
     has
    0.40
    ISupport
    0.40
     may
    0.39
    Activations Density 0.315%

    No Known Activations