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. 21-GEMMASCOPE-RES-16K
    6. 11939
    Prev
    Next
    INDEX
    Explanations

    references to the phrase "a/an" to denote a specific type or instance of something

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 21-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_21/width_16k/average_l0_129
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.hook_resid_post
    Hook Layer
    21
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Penga
    -0.61
     obligado
    -0.52
     contribución
    -0.50
    ėjimas
    -0.50
    anjutnya
    -0.50
    zzleHttp
    -0.49
    ísimo
    -0.49
    bentar
    -0.48
     dreapta
    -0.47
     apoder
    -0.47
    POSITIVE LOGITS
     various
    0.59
    __(/*!
    0.58
     others
    0.56
     other
    0.53
     regional
    0.50
     getCity
    0.50
     certain
    0.48
     previously
    0.47
     betweenstory
    0.46
     previous
    0.45
    Activations Density 0.561%

    No Known Activations