© 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. 21-GEMMASCOPE-RES-16K
    11. 12722
    Prev
    Next
    INDEX
    Explanations

    discussions about political ideologies and their evolving nature

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 21-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_21/width_16k/average_l0_70
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.hook_resid_post
    Hook Layer
    21
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ValueStyle
    -0.86
     InputDecoration
    -0.74
    HtmlAttribute
    -0.70
     prochains
    -0.63
    原始内容存档于
    -0.60
    ViewInit
    -0.59
    ]")]
    -0.58
    extAlignment
    -0.58
     AsyncTask
    -0.57
    ORAGE
    -0.57
    POSITIVE LOGITS
     years
    1.86
     earlier
    1.77
     decades
    1.70
     vroeger
    1.53
    earlier
    1.46
    years
    1.45
    Years
    1.44
     autrefois
    1.40
     YEARS
    1.38
     früher
    1.32
    Activations Density 0.820%

    No Known Activations