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. 12871
    Prev
    Next
    INDEX
    Explanations

    the presence of application-related terminology or structure in the text

    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
    品
    -0.47
     val
    -0.47
     a
    -0.47
     more
    -0.47
    ámos
    -0.46
    пак
    -0.45
     they
    -0.45
     Do
    -0.44
     T
    -0.44
     its
    -0.42
    POSITIVE LOGITS
    Hentet
    1.04
     Normdatei
    0.80
    Scénario
    0.79
     estekak
    0.76
     OFDb
    0.75
     NDEBUG
    0.72
     Superhost
    0.70
     ostavi
    0.70
    ⓧ
    0.70
     ویکی‌پدی
    0.69
    Activations Density 0.206%

    No Known Activations