© 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. 24-GEMMASCOPE-RES-16K
    11. 14430
    Prev
    Next
    INDEX
    Explanations

    references to social concepts and issues

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

    "social" and then a topic

    np_acts-logits-general · gemini-2.0-flash

    social media and sciences

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 24-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_24/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.24.hook_resid_post
    Hook Layer
    24
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    tagHelperRunner
    -0.74
    })();
    -0.59
    rstrip
    -0.54
    gnancy
    -0.54
    脚注の使い方
    -0.54
    GOTREF
    -0.53
    KES
    -0.52
     Zus
    -0.51
     VIDEOTAPE
    -0.51
    ImageContext
    -0.51
    POSITIVE LOGITS
     media
    0.67
     sciences
    0.61
     distancing
    0.60
     Media
    0.56
     MEDIA
    0.52
     justice
    0.52
     worker
    0.51
     Sciences
    0.51
     engineering
    0.51
     scientists
    0.49
    Activations Density 0.072%

    No Known Activations