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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 5693
    Prev
    Next
    INDEX
    Explanations

    situations involving safety and security risks

    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
     Thereafter
    -0.88
     Subsequently
    -0.85
     extant
    -0.81
     annum
    -0.79
     concomitant
    -0.78
     thereafter
    -0.77
     consequent
    -0.76
     thereupon
    -0.75
    StoryboardSegue
    -0.71
     thereby
    -0.71
    POSITIVE LOGITS
     FOX
    0.87
    FOX
    0.76
     Officials
    0.71
     lawmakers
    0.69
    Officials
    0.69
     alright
    0.68
     Tuesday
    0.66
     crews
    0.66
     Wednesday
    0.64
     Investigators
    0.64
    Activations Density 0.102%

    No Known Activations