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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 6873
    Prev
    Next
    INDEX
    Explanations

    instances of line break or paragraph break tags in the document

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

    HTML line breaks

    np_acts-logits-general · gemini-2.0-flash

    line break tags

    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
    Revenir
    -0.70
     (?,
    -0.69
    {(-
    -0.68
    __":
    -0.68
    __':
    -0.68
    "](
    -0.67
    ="(
    -0.67
     ?>>
    -0.67
    =$((
    -0.66
    ={({
    -0.65
    POSITIVE LOGITS
    br
    1.05
    Br
    0.85
     Br
    0.81
     Brink
    0.72
     Brind
    0.72
     br
    0.72
     οποία
    0.69
    rrggbb
    0.69
     Brü
    0.65
     Bronson
    0.64
    Activations Density 0.027%

    No Known Activations