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. 24-GEMMASCOPE-RES-16K
    6. 14643
    Prev
    Next
    INDEX
    Explanations

    terms related to job positions and professional roles in government and organizations

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

    preceding organizations or locations

    np_acts-logits-general · gemini-2.0-flash

    specific organizations and affiliations

    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
    脚注の使い方
    -0.61
    soever
    -0.61
     saja
    -0.56
    GEBURTSDATUM
    -0.56
     eğer
    -0.56
     yoksa
    -0.56
    ]}"
    -0.55
    endforeach
    -0.55
    hichever
    -0.54
     Yesterday
    -0.54
    POSITIVE LOGITS
     before
    0.98
     where
    0.97
     earning
    0.93
     until
    0.84
    where
    0.84
     helping
    0.83
     becoming
    0.83
    before
    0.82
     voordat
    0.80
    becoming
    0.78
    Activations Density 0.422%

    No Known Activations