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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 21-GEMMASCOPE-RES-16K
    6. 13443
    Prev
    Next
    INDEX
    Explanations

    information related to HIV subtypes and their prevalence or characteristics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 21-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_21/width_16k/average_l0_70
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.hook_resid_post
    Hook Layer
    21
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    enumi
    -0.59
    fjspx
    -0.59
    enumii
    -0.54
     дописавши
    -0.50
    eqn
    -0.50
    sejarah
    -0.50
    Geplaatst
    -0.50
    GeoNames
    -0.47
    toid
    -0.46
     Depends
    -0.46
    POSITIVE LOGITS
     prevalent
    1.99
     common
    1.82
     predominant
    1.66
     predominate
    1.63
     dominant
    1.62
    common
    1.61
     prevalence
    1.51
     widespread
    1.49
    dominant
    1.47
     ubiquitous
    1.45
    Activations Density 0.712%

    No Known Activations