© 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-2-2B
    7. Residual Stream - 16k
    9. 15-GEMMASCOPE-RES-16K
    11. 8999
    Prev
    Next
    INDEX
    Explanations

    terms related to motion and distance

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 15-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_15/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.15.hook_resid_post
    Hook Layer
    15
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    :+:
    -0.77
    __":
    -0.71
    Datuak
    -0.65
    ########.
    -0.65
    #+#
    -0.63
    __':
    -0.61
    存于互联网档案馆
    -0.61
    脚注の使い方
    -0.60
     kasarigan
    -0.59
     مرئيه
    -0.59
    POSITIVE LOGITS
     oneself
    0.75
     someone
    0.61
     especially
    0.59
    という意味
    0.57
     чого
    0.57
    的意思
    0.56
     Majefty
    0.56
     sth
    0.56
    하다
    0.56
    antMatchers
    0.52
    Activations Density 0.155%

    No Known Activations