Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B-IT
    4. Residual Stream - 16k
    5. 31-GEMMASCOPE-RES-16K
    6. 16382
    Prev
    Next
    INDEX
    Explanations

    phrases related to policies and legal frameworks

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

    Text enclosed in quotation marks

    np_acts-logits-general · gemini-2.0-flash

    quotation marks and titles

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 31-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-it-res/layer_31/width_16k/average_l0_76
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.31.hook_resid_post
    Hook Layer
    31
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    expandindo
    -0.65
     $_"
    -0.55
    majánló
    -0.54
     NDEBUG
    -0.53
     AppCompatTheme
    -0.51
    ロウィン
    -0.50
     incrí
    -0.49
     témoig
    -0.49
     />,
    -0.49
    attutto
    -0.48
    POSITIVE LOGITS
     “
    2.39
     "
    2.38
     „
    1.98
     «
    1.89
     '
    1.79
     ‘
    1.77
    「
    1.73
     ``
    1.60
     「
    1.57
     \"
    1.47
    Activations Density 1.310%

    No Known Activations