Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 18-GEMMASCOPE-RES-16K
    6. 14696
    Prev
    Next
    INDEX
    Explanations

    the beginning of a new segment or section in the text

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

    Follows a colon, quote, or bracket

    np_acts-logits-general · gemini-2.0-flash

    academic and medical contexts

    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
    PhysRevLett
    -0.72
     فريبيس
    -0.69
     bezeichneter
    -0.69
    солю
    -0.68
    findpost
    -0.68
    ConstraintMaker
    -0.63
    bootstrapcdn
    -0.63
    InjectAttribute
    -0.63
    Geplaatst
    -0.62
    новништво
    -0.61
    POSITIVE LOGITS
     oil
    0.76
     gummies
    0.65
     Oil
    0.60
    roleum
    0.51
    issance
    0.49
    ();
    
    
    0.49
    SpringBootTest
    0.48
    ทย
    0.47
     OIL
    0.47
    rull
    0.46
    Activations Density 0.010%

    No Known Activations