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. 20-GEMMASCOPE-RES-16K
    6. 114
    Prev
    Next
    INDEX
    Explanations

    phrases related to rights, waivers, and legal consequences

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

    Preceding words of "these" or "those"

    np_acts-logits-general · gemini-2.0-flash

    demonstratives like these and those

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     resourceCulture
    -0.74
    RegressionTest
    -0.68
    />";
    -0.60
     CreateTagHelper
    -0.59
    principalColumn
    -0.58
     createState
    -0.57
    __":
    
    -0.57
    ']>;
    -0.56
    ngdoc
    -0.56
    volles
    -0.55
    POSITIVE LOGITS
     these
    3.54
     These
    3.07
    these
    3.07
    These
    2.99
     THESE
    2.62
    これらの
    2.46
    这些
    2.44
    這些
    2.44
     этих
    2.13
     those
    2.09
    Activations Density 2.372%

    No Known Activations