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. 25-GEMMASCOPE-RES-16K
    6. 8081
    Prev
    Next
    INDEX
    Explanations

    elements related to metrics or statistical data

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 25-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_25/width_16k/average_l0_116
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.hook_resid_post
    Hook Layer
    25
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Monfieur
    -0.88
     myſelf
    -0.88
     Efq
    -0.88
     auffi
    -0.76
     purpoſe
    -0.69
    ^(@)
    -0.66
     ſtand
    -0.65
     themſelves
    -0.63
    ſelf
    -0.63
     ſet
    -0.63
    POSITIVE LOGITS
    4
    1.03
    3
    1.02
    6
    0.98
    5
    0.97
    7
    0.92
    8
    0.86
    2
    0.80
    9
    0.75
    1
    0.70
    0
    0.56
    Activations Density 0.337%

    No Known Activations