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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlogSlackPrivacy & 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. 18-GEMMASCOPE-RES-16K
    6. 10643
    Prev
    Next
    INDEX
    Explanations

    numeric values and identifiers commonly associated with data or system configurations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.hook_resid_post
    Hook Layer
    18
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     ]];
    -0.56
    aarrggbb
    -0.56
     utafitiHapana
    -0.56
    richTextPanel
    -0.55
    ItemBackground
    -0.53
    例句
    -0.52
     defaultstate
    -0.50
     Ptole
    -0.49
     UnityEditor
    -0.49
     comigo
    -0.49
    POSITIVE LOGITS
    AccessorTable
    0.64
     propOrder
    0.60
     dikem
    0.57
    OURCE
    0.55
    FailureListener
    0.52
    ilmente
    0.50
    licated
    0.46
     Alexander
    0.46
     whole
    0.46
     heavily
    0.46
    Activations Density 0.267%

    No Known Activations