Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 9-GEMMASCOPE-RES-16K
    6. 15094
    Prev
    Next
    INDEX
    Explanations

    phrases and concepts related to customer support and documentation resources

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 9-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_9/width_16k/average_l0_73
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.9.hook_resid_post
    Hook Layer
    9
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    herin
    -0.50
    djangoproject
    -0.48
     hesap
    -0.48
     Computation
    -0.46
    λογ
    -0.45
     confetti
    -0.45
     computation
    -0.45
    sampling
    -0.45
     computationally
    -0.43
     لينك
    -0.43
    POSITIVE LOGITS
     instructions
    0.91
     instruction
    0.90
     tutorials
    0.84
     instructional
    0.79
     guides
    0.79
     tutorial
    0.77
     AssemblyCulture
    0.76
    instruction
    0.74
     Instruction
    0.73
    Instruction
    0.72
    Activations Density 0.632%

    No Known Activations