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. 18-GEMMASCOPE-RES-16K
    6. 3604
    Prev
    Next
    INDEX
    Explanations

    references to specific individuals and their associated characteristics in a narrative context

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

    of nationality or profession

    np_acts-logits-general · gemini-2.0-flash

    nationalities and professions

    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
     mergeFrom
    -0.57
     or
    -0.51
    گي
    -0.36
     such
    -0.35
    impl
    -0.34
    这样的
    -0.34
    گی
    -0.33
     Gorge
    -0.33
    msgid
    -0.33
    ivamente
    -0.33
    POSITIVE LOGITS
    WriteBarrier
    0.98
    jsonwebtoken
    0.83
     kasarigan
    0.79
    MENAFN
    0.76
    SuppressMessage
    0.75
     kelahiran
    0.75
    HasAnnotation
    0.74
     nargin
    0.74
     referrerpolicy
    0.74
    Bioaccumulative
    0.73
    Activations Density 0.203%

    No Known Activations