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. 22-GEMMASCOPE-RES-16K
    6. 10912
    Prev
    Next
    INDEX
    Explanations

    phrases related to conclusions and judgments

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

    Drawing conclusions or reaching conclusions

    np_acts-logits-general · gemini-2.0-flash

    draw a conclusion

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 22-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_22/width_16k/average_l0_72
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.hook_resid_post
    Hook Layer
    22
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    HasForeignKey
    -0.61
    EnableWeb
    -0.50
    دانشنامهٔ
    -0.50
    ืม
    -0.50
    opedia
    -0.49
     parseFrom
    -0.48
     huyền
    -0.48
    __.__
    -0.48
    adox
    -0.47
    ruecos
    -0.47
    POSITIVE LOGITS
     conclusion
    1.65
     conclusions
    1.59
     Reach
    1.53
    Reach
    1.50
     reach
    1.50
     reached
    1.49
     reaching
    1.41
    reach
    1.40
    Reaching
    1.39
     Reaching
    1.37
    Activations Density 0.574%

    No Known Activations