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. 8587
    Prev
    Next
    INDEX
    Explanations

    titles and positions of authority or leadership roles

    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
    RectangleBorder
    -0.57
    ãng
    -0.52
     salg
    -0.50
    lidean
    -0.49
    isle
    -0.48
    ListOf
    -0.46
    AnchorStyles
    -0.45
    jboss
    -0.45
     comp
    -0.45
     impar
    -0.45
    POSITIVE LOGITS
    CodeAttribute
    0.78
    QMetaType
    0.73
     apologised
    0.70
    AutoScaleMode
    0.67
    GeneratedCode
    0.65
     démission
    0.64
    ('/:
    0.63
    حوالہ
    0.63
    seamnă
    0.62
    Lähteet
    0.62
    Activations Density 0.091%

    No Known Activations