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. 14195
    Prev
    Next
    INDEX
    Explanations

    technical terms and jargon related to programming and processes

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

    Followed by the letter "p"

    np_acts-logits-general · gemini-2.0-flash

    `pip`, `per`, `pes`, `ps`

    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
     getP
    -0.46
     Référence
    -0.46
     protoimpl
    -0.45
     متعلقه
    -0.43
    EndProject
    -0.43
    ngrx
    -0.43
     setuptools
    -0.42
    dP
    -0.42
    assertRaises
    -0.41
     hObject
    -0.41
    POSITIVE LOGITS
    ping
    0.78
    ped
    0.77
    per
    0.71
    pe
    0.70
    pes
    0.68
    po
    0.68
    peur
    0.67
    pos
    0.66
    pie
    0.64
    pi
    0.64
    Activations Density 0.491%

    No Known Activations