© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 2-GEMMASCOPE-RES-16K
    6. 12709
    Prev
    Next
    INDEX
    Explanations

    instances of the word "pack" or related variations indicating a collection or group

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 2-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_2/width_16k/average_l0_67
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.hook_resid_post
    Hook Layer
    2
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    expandindo
    -0.35
     Verme
    -0.33
    ęki
    -0.33
    OGND
    -0.33
    ınt
    -0.33
     viewDidLoad
    -0.33
    řev
    -0.32
     agrícolas
    -0.32
     frío
    -0.31
     avena
    -0.31
    POSITIVE LOGITS
     Pack
    2.67
     pack
    2.64
     PACK
    2.59
    Pack
    2.53
    pack
    2.44
     pak
    2.39
     Pak
    2.34
     Packs
    2.34
     packs
    2.33
    PACK
    2.33
    Activations Density 0.499%

    No Known Activations