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. 4261
    Prev
    Next
    INDEX
    Explanations

    phrases related to dietary choices and health-related discussions

    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
     mergeFrom
    -0.64
    RectangleBorder
    -0.59
    ifikationen
    -0.59
     nawr
    -0.59
     Expédié
    -0.52
    REMARKS
    -0.51
    ſelf
    -0.50
    onViewCreated
    -0.50
     podjela
    -0.49
    äher
    -0.47
    POSITIVE LOGITS
     opt
    1.32
     Opt
    1.13
     consider
    1.13
     opting
    1.09
     Consider
    1.07
    Consider
    1.06
    Opt
    1.02
     invest
    1.01
    opt
    0.97
    consider
    0.94
    Activations Density 0.167%

    No Known Activations