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. 16-GEMMASCOPE-RES-16K
    6. 8884
    Prev
    Next
    INDEX
    Explanations

    references to items being named or labeled

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Precedes words after "called"

    np_acts-logits-general · gemini-2.0-flash

    introducing the name or designation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 16-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_16/width_16k/average_l0_78
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.16.hook_resid_post
    Hook Layer
    16
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ValueStyle
    -0.58
    出版年
    -0.55
     Asie
    -0.52
     Houſe
    -0.51
     Avez
    -0.50
     Sopho
    -0.50
     Pentecost
    -0.49
     Yoh
    -0.48
     houſe
    -0.48
     Uff
    -0.47
    POSITIVE LOGITS
     “
    1.04
     "
    1.04
     «
    0.88
     „
    0.82
     ‘
    0.81
    ]=="
    0.77
    ']='
    0.73
     '
    0.71
    "=>"
    0.70
    「
    0.70
    Activations Density 0.157%

    No Known Activations