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. 7-GEMMASCOPE-RES-16K
    6. 15556
    Prev
    Next
    INDEX
    Explanations

    references to body parts, especially the back and associated discomfort or injuries

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 7-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_7/width_16k/average_l0_69
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.7.hook_resid_post
    Hook Layer
    7
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    atering
    -0.54
    Swal
    -0.51
    OrBuilder
    -0.50
     Circle
    -0.50
    Insee
    -0.50
    prache
    -0.50
    simile
    -0.49
    न्द्र
    -0.49
    Circle
    -0.48
    antino
    -0.48
    POSITIVE LOGITS
    StoryboardSegue
    0.93
    liosis
    0.89
    ]")]
    0.81
     shoulders
    0.76
     Rücken
    0.76
    bootstrapcdn
    0.75
     punggung
    0.74
    Shoulder
    0.69
     shoulder
    0.69
     مشين
    0.67
    Activations Density 0.233%

    No Known Activations