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-2-9B
    4. Residual Stream - 16k
    5. 28-GEMMASCOPE-RES-16K
    6. 4133
    Prev
    Next
    INDEX
    Explanations

    specific medical terms and phrases related to cytotoxicity and treatment outcomes

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

    Content after "Abstract" or "Introduction"

    np_acts-logits-general · gemini-2.0-flash

    abstract

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 28-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_28/width_16k/average_l0_119
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.28.hook_resid_post
    Hook Layer
    28
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     للمعارف
    -0.54
    UrlResolution
    -0.52
     pitä
    -0.50
     المعيارى
    -0.49
    twimg
    -0.47
    Kanpo
    -0.46
    хьтан
    -0.46
    MethodManager
    -0.45
    whatever
    -0.44
     hayas
    -0.44
    POSITIVE LOGITS
    Abstract
    0.98
     Abstract
    0.92
     ABSTRACT
    0.85
    ABSTRACT
    0.82
     abstract
    0.73
     abstracts
    0.69
     Abstracts
    0.65
    abstract
    0.65
     authors
    0.61
    摘要
    0.59
    Activations Density 1.448%

    No Known Activations