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. 33-GEMMASCOPE-RES-16K
    6. 11313
    Prev
    Next
    INDEX
    Explanations

    terms related to programming and software development, particularly those involving specific programming languages and tools

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 33-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_33/width_16k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.33.hook_resid_post
    Hook Layer
    33
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    PhysRevLett
    -0.44
    Datuak
    -0.43
    .*")]
    -0.42
    omitempty
    -0.40
    équilibre
    -0.39
    sizeCache
    -0.39
     bautizo
    -0.38
     consciência
    -0.38
    Tembelea
    -0.38
     illustrazione
    -0.35
    POSITIVE LOGITS
     version
    0.64
    自带
    0.54
     Version
    0.54
    ®
    0.53
     compatible
    0.52
     native
    0.51
     default
    0.51
     versión
    0.50
    tanleria
    0.50
     versão
    0.49
    Activations Density 0.899%

    No Known Activations