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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 14759
    Prev
    Next
    INDEX
    Explanations

    references to medical equipment and personal protective gear

    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
     constitution
    -0.48
     sains
    -0.45
    ">'.$
    -0.43
    HANDLE
    -0.42
    contrib
    -0.42
    }}}}
    -0.42
     htmlFor
    -0.42
    suz
    -0.41
    servez
    -0.41
    िने
    -0.41
    POSITIVE LOGITS
     متعلقه
    0.87
     utafitiHapana
    0.86
    GEBURTSDATUM
    0.82
    tvguidetime
    0.82
    
    0.81
    évaluateur
    0.81
    rungsseite
    0.79
    SourceChecksum
    0.79
    awaiter
    0.77
     snippetHide
    0.76
    Activations Density 0.422%

    No Known Activations