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

    Neuronpedia

    APICircuit 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. 5-GEMMASCOPE-RES-16K
    6. 16182
    Prev
    Next
    INDEX
    Explanations

    the colon character used for designating key-value pairs in code or data representations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.5.hook_resid_post
    Hook Layer
    5
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ↵
    -0.54
    ↵↵↵
    -0.45
    -
    -0.45
     
    -0.42
    oben
    -0.39
    to
    -0.39
     '
    -0.39
     m
    -0.38
    ילד
    -0.37
    Intérieur
    -0.36
    POSITIVE LOGITS
    SBATCH
    1.11
    endphp
    1.08
    sizeCache
    1.06
    NameInMap
    1.04
     AssemblyTitle
    1.02
    UnusedPrivate
    0.99
    Vidite
    0.98
     nahilalakip
    0.96
    ISupport
    0.94
    posedge
    0.94
    Activations Density 0.065%

    No Known Activations