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. 15639
    Prev
    Next
    INDEX
    Explanations

    verbs associated with change or modification

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

    change or transformation

    np_acts-logits-general · gemini-2.0-flash

    change, transition, or opposition

    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
    FSA
    -0.52
    zsh
    -0.47
    DataURL
    -0.46
     AppModule
    -0.46
     didst
    -0.45
     struggling
    -0.45
    setInt
    -0.45
     Manually
    -0.44
    lama
    -0.43
    Rhestr
    -0.43
    POSITIVE LOGITS
     CreateTagHelper
    0.81
     itself
    0.73
     gynhyrchwyd
    0.68
     '\\;'
    0.68
    клопе
    0.65
    kuuta
    0.65
     Itself
    0.62
    +:+
    0.61
    AddTagHelper
    0.60
    )];
    
    0.60
    Activations Density 0.705%

    No Known Activations