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. 15644
    Prev
    Next
    INDEX
    Explanations

    conjunctive phrases and transitions that indicate the addition of information

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

    that start sentences and add information

    np_acts-logits-general · gemini-2.0-flash

    additive conjunctions

    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
     FetchType
    -0.66
    jsonwebtoken
    -0.59
     getPosition
    -0.59
    énus
    -0.59
     barbati
    -0.59
     specchio
    -0.58
    WebControls
    -0.57
    Cordialement
    -0.56
    </caption>
    -0.56
     Kirkpatrick
    -0.56
    POSITIVE LOGITS
     also
    0.79
     nahilalakip
    0.73
    همچنین
    0.66
    Also
    0.64
    Additionally
    0.62
     Also
    0.62
    also
    0.62
    由于
    0.60
     دیکھیے
    0.60
     since
    0.59
    Activations Density 0.246%

    No Known Activations