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
    4. Residual Stream - 16k
    5. 31-GEMMASCOPE-RES-16K
    6. 16345
    Prev
    Next
    INDEX
    Explanations

    information related to cellular responses and treatments

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

    scientific or medical research terminology related to cell processes and experimental procedures.

    oai_token-act-pair · claude-3-5-haiku-20241022Triggered by @neilrathi
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 31-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_31/width_16k/average_l0_114
    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
    IUrlHelper
    -0.68
     defaultstate
    -0.65
    protoimpl
    -0.59
     PagesJaunes
    -0.51
    ReusableCell
    -0.51
    StoryboardSegue
    -0.49
    IVEREF
    -0.48
    thâu
    -0.47
     OFDb
    -0.47
    Ӕ
    -0.47
    POSITIVE LOGITS
     stimuli
    0.68
     treatment
    0.68
     stimulation
    0.63
     treatments
    0.61
     exposure
    0.60
     stressors
    0.59
     Behandlung
    0.59
     stimulus
    0.59
     TREATMENT
    0.58
     administration
    0.53
    Activations Density 2.637%

    No Known Activations