© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B-IT
    7. Residual Stream - 131k
    9. 20-GEMMASCOPE-RES-131K
    11. 28387
    Prev
    Next
    INDEX
    Explanations

    terms related to hypoxic injury and its effects on brain and heart tissues

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

    tissue damage and death

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_131k/average_l0_81
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Administrativna
    -0.53
     kaarangay
    -0.47
     libremente
    -0.45
     cremallera
    -0.44
    Personendaten
    -0.43
    LookAnd
    -0.43
    ManagedBean
    -0.42
     mentions
    -0.42
    orianCalendar
    -0.41
     cuchara
    -0.41
    POSITIVE LOGITS
     damage
    0.64
    damage
    0.63
     destruction
    0.51
     Damage
    0.51
    Damage
    0.50
    injury
    0.49
     injury
    0.48
    destruction
    0.48
    amaged
    0.47
    ésult
    0.46
    Activations Density 0.171%

    No Known Activations