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. 22-GEMMASCOPE-RES-16K
    6. 13933
    Prev
    Next
    INDEX
    Explanations

    components related to genetic or molecular analysis

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 22-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_22/width_16k/average_l0_72
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.hook_resid_post
    Hook Layer
    22
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     AdapterView
    -0.63
     doInBackground
    -0.61
     pratique
    -0.60
     artesanales
    -0.58
    ########.
    -0.57
     Rink
    -0.57
     econô
    -0.56
     AsyncTask
    -0.55
    Fio
    -0.54
     dAtA
    -0.54
    POSITIVE LOGITS
     chromatin
    0.81
     transcriptional
    0.78
     transcription
    0.75
     DNA
    0.70
     repressive
    0.68
    Transcription
    0.67
     Transcription
    0.66
     histone
    0.66
    transcription
    0.65
     binding
    0.62
    Activations Density 1.233%

    No Known Activations