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

    Neuronpedia

    APIAssistant AxisNEWCircuit 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. 24-GEMMASCOPE-RES-16K
    6. 2238
    Prev
    Next
    INDEX
    Explanations

    mathematical references and terms related to infections caused by Mycobacterium species

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

    Follows periods preceding scientific names

    np_acts-logits-general · gemini-2.0-flash

    Mycobacterium, tuberculosis, smegmatis

    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
     CreateTagHelper
    -0.61
    findpost
    -0.60
    writeFieldEnd
    -0.57
     mention
    -0.56
    prefixer
    -0.54
     sánh
    -0.51
    ContentAlignment
    -0.51
    onViewCreated
    -0.51
    WithMany
    -0.50
     modified
    -0.50
    POSITIVE LOGITS
     Madness
    0.69
     Mayhem
    0.67
    Autoritní
    0.64
    ########.
    0.64
     Administrativna
    0.54
     hashlib
    0.54
     mayhem
    0.53
     MMM
    0.52
     MCC
    0.51
     aparte
    0.51
    Activations Density 0.536%

    No Known Activations