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-2-2B
    4. Residual Stream - 16k
    5. 16-GEMMASCOPE-RES-16K
    6. 205
    Prev
    Next
    INDEX
    Explanations

    scientific terms related to quantum mechanics and engineering concepts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    relating to accomplishment or achievement

    np_acts-logits-general · gemini-2.0-flash

    successful outcomes

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 16-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_16/width_16k/average_l0_78
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.16.hook_resid_post
    Hook Layer
    16
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    BeginContext
    -0.58
    rinfo
    -0.57
    TagMode
    -0.54
    BagConstraints
    -0.53
    pecially
    -0.52
    eschön
    -0.52
    astrar
    -0.52
     dovuto
    -0.51
     beginnetje
    -0.51
    بیشتر
    -0.51
    POSITIVE LOGITS
     successfully
    1.18
     successful
    0.96
    successfully
    0.95
     Successfully
    0.93
    Successfully
    0.83
     succes
    0.83
     Successful
    0.81
    成功
    0.81
     sucess
    0.78
     demonstrated
    0.77
    Activations Density 1.039%

    No Known Activations