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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 24-GEMMASCOPE-RES-16K
    6. 8146
    Prev
    Next
    INDEX
    Explanations

    anatomical references related to the human body

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

    Parts of the human body

    np_acts-logits-general · gemini-2.0-flash

    external body parts

    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
    olisian
    -0.55
     Grand
    -0.53
     henkil
    -0.53
    ecera
    -0.52
     jäsen
    -0.51
    стви
    -0.51
    INCREF
    -0.50
     plais
    -0.49
     hånd
    -0.49
     snippetHide
    -0.48
    POSITIVE LOGITS
     region
    0.92
     muscles
    0.87
     bones
    0.83
     area
    0.83
     bone
    0.78
    bone
    0.77
    region
    0.74
    bones
    0.74
     Region
    0.73
     AREA
    0.70
    Activations Density 0.270%

    No Known Activations