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. 2-GEMMASCOPE-RES-16K
    6. 8537
    Prev
    Next
    INDEX
    Explanations

    names of individuals, particularly those associated with sports or legal contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 2-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_2/width_16k/average_l0_67
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.hook_resid_post
    Hook Layer
    2
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    yntaxException
    -0.56
     Shard
    -0.52
     Gogh
    -0.52
     StatelessWidget
    -0.50
    Datuak
    -0.49
    izr
    -0.49
    Spark
    -0.48
     Vertigo
    -0.48
    Bey
    -0.48
    Zinc
    -0.47
    POSITIVE LOGITS
     Johnny
    0.79
     Bobby
    0.75
     Tommy
    0.73
    Johnny
    0.72
    Bobby
    0.69
    Tommy
    0.68
     Jerry
    0.68
    Jerry
    0.63
     Ronnie
    0.62
    tommy
    0.61
    Activations Density 0.583%

    No Known Activations