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

    Neuronpedia

    APICircuit 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. 16-GEMMASCOPE-RES-16K
    6. 15808
    Prev
    Next
    INDEX
    Explanations

    conditional statements suggesting hypothetical scenarios

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

    "as if"

    np_acts-logits-general · gemini-2.0-flash

    introducing hypothetical comparisons

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 16-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_16/width_16k/average_l0_78
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.16.hook_resid_post
    Hook Layer
    16
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     apparently
    -0.55
     reportedly
    -0.54
     Apparently
    -0.54
     spalle
    -0.54
     tearDown
    -0.52
    apparently
    -0.52
     cest
    -0.51
    GetEnumerator
    -0.51
    Apparently
    -0.50
     gambe
    -0.50
    POSITIVE LOGITS
     CreateTagHelper
    0.79
    NUMX
    0.73
    ंदीखरीदारी
    0.73
     المعيارى
    0.72
    AnchorStyles
    0.68
    AddTagHelper
    0.66
    ########.
    0.65
     оригіналу
    0.64
    醐
    0.64
     فريبيس
    0.64
    Activations Density 0.120%

    No Known Activations