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. 24-GEMMASCOPE-RES-16K
    6. 4601
    Prev
    Next
    INDEX
    Explanations

    references to legal proceedings and medical reports involving a specific individual

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

    "La" followed by another word

    np_acts-logits-general · gemini-2.0-flash

    La followed by letters

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 24-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_24/width_16k/average_l0_73
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.hook_resid_post
    Hook Layer
    24
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    TextWatcher
    -0.48
    lien
    -0.47
    WaitGroup
    -0.46
    Referencies
    -0.45
     withRouter
    -0.45
    UnusedPrivate
    -0.44
     lì
    -0.44
    IBOutlet
    -0.44
    lí
    -0.43
    Lien
    -0.43
    POSITIVE LOGITS
     La
    3.13
    La
    3.03
     la
    2.98
    la
    2.43
     LA
    2.33
    LA
    2.21
     Ла
    2.04
    Ла
    1.89
     ла
    1.73
     Laf
    1.67
    Activations Density 0.402%

    No Known Activations