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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    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. 11226
    Prev
    Next
    INDEX
    Explanations

    conditional phrases and options related to problem-solving or decision-making

    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
     dessutom
    -0.51
     nejen
    -0.51
     mukana
    -0.45
     notamment
    -0.45
     Особенно
    -0.44
     besonder
    -0.43
     moreover
    -0.43
     중요
    -0.43
     importantly
    -0.42
     insbesondere
    -0.42
    POSITIVE LOGITS
    諦
    0.66
    干脆
    0.66
    alternative
    0.65
     wait
    0.65
     alternatives
    0.65
    걍
    0.64
     alternative
    0.64
     simply
    0.62
    alternate
    0.62
     Alternatives
    0.62
    Activations Density 0.753%

    No Known Activations