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-2-2B
    4. Residual Stream - 16k
    5. 5-GEMMASCOPE-RES-16K
    6. 7479
    Prev
    Next
    INDEX
    Explanations

    phrases that emphasize the concept of "matter" in terms of importance or significance in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.5.hook_resid_post
    Hook Layer
    5
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    vivi
    -0.83
     Villanueva
    -0.82
    ruitment
    -0.79
    ]++;
    -0.79
    cifix
    -0.79
    MemoryWarning
    -0.76
     whiteness
    -0.75
     Alain
    -0.74
    verläs
    -0.74
    newblock
    -0.72
    POSITIVE LOGITS
     matter
    2.40
    matter
    2.19
     Matter
    2.13
     matters
    2.08
    Matter
    2.08
     MATTER
    1.99
     Matters
    1.91
    matters
    1.87
     MATTERS
    1.74
    Matters
    1.73
    Activations Density 0.070%

    No Known Activations