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. 16-GEMMASCOPE-RES-16K
    6. 6692
    Prev
    Next
    INDEX
    Explanations

    references to procedures, risks, and limitations in technical or legal contexts

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

    Followed by "so"

    np_acts-logits-general · gemini-2.0-flash

    consequence marker so

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 16-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_16/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.16.hook_resid_post
    Hook Layer
    16
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     ligiloj
    -0.85
    "]);
    
    -0.83
     Efq
    -0.81
     Sarm
    -0.80
    }}$\\
    -0.79
     Theſe
    -0.79
     }}$}
    -0.76
    MIDDLEWARE
    -0.76
     ་་
    -0.74
    ."]
    -0.73
    POSITIVE LOGITS
     so
    1.73
     So
    1.28
    So
    1.24
    所以
    1.17
    so
    1.14
     поэтому
    1.13
     nên
    1.10
    所以在
    1.01
    ないので
    1.01
    いたので
    1.01
    Activations Density 0.686%

    No Known Activations