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. 15-GEMMASCOPE-RES-16K
    6. 12665
    Prev
    Next
    INDEX
    Explanations

    programming language constructs and key attributes related to data structures and message handling

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 15-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_15/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.15.hook_resid_post
    Hook Layer
    15
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    withstanding
    -1.13
    которые
    -0.74
    UnusedPrivate
    -0.66
    tably
    -0.65
    viembre
    -0.63
    ".
    
    -0.63
    queous
    -0.61
    StreetMap
    -0.61
    AndView
    -0.61
    ftagPool
    -0.60
    POSITIVE LOGITS
     ویکی‌پدیا
    0.78
     энциклопедия
    0.73
     صوتيه
    0.65
    NewUrlParser
    0.65
     SafeMath
    0.64
    lloworld
    0.61
    достатки
    0.60
    conomie
    0.60
    дравствуйте
    0.60
    CADE
    0.57
    Activations Density 0.759%

    No Known Activations