© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 24-GEMMASCOPE-RES-16K
    11. 6555
    Prev
    Next
    INDEX
    Explanations

    references to blood-related terms and cellular components

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

    "Hem" followed by biological terms

    np_acts-logits-general · gemini-2.0-flash

    hem-ocytes, hem-ophilia, hem-angio

    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
    ChildScrollView
    -0.60
    saraba
    -0.57
     gynhyrchwyd
    -0.55
    FieldBuilder
    -0.54
    ribune
    -0.53
    forChild
    -0.53
    いくら
    -0.52
    parsedMessage
    -0.51
    ymi
    -0.51
     rospy
    -0.49
    POSITIVE LOGITS
    StoryboardSegue
    0.55
    templateUrl
    0.51
     casado
    0.49
    новништво
    0.49
     CWE
    0.48
    rdom
    0.48
     famí
    0.47
     UIImageView
    0.46
     [*]
    0.46
     الرياضيه
    0.45
    Activations Density 0.203%

    No Known Activations