© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 2-GEMMASCOPE-RES-16K
    11. 8271
    Prev
    Next
    INDEX
    Explanations

    lines or tokens that represent different types of compiler or preprocessor directives

    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
    Telefax
    -0.43
     ſind
    -0.42
    zaam
    -0.41
    drawSprites
    -0.41
    neuf
    -0.40
    assertFalse
    -0.39
     аккура
    -0.38
    一小
    -0.38
     BioLib
    -0.38
    Gemeinden
    -0.38
    POSITIVE LOGITS
    #
    1.62
    #
    1.05
    //
    0.85
    IntoConstraints
    0.80
    /*
    0.79
    //
    0.75
     []:
    0.69
    ScopeManager
    0.69
    fjspx
    0.65
    /**
    0.64
    Activations Density 0.206%

    No Known Activations