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. 20-GEMMASCOPE-RES-16K
    6. 2211
    Prev
    Next
    INDEX
    Explanations

    references to political interventions and their consequences

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

    negativity or harm

    np_acts-logits-general · gemini-2.0-flash

    negatively affecting outcomes

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    suddenly
    -0.53
     suddenly
    -0.53
     estekak
    -0.52
    XmlAccessType
    -0.51
     soudain
    -0.51
     unexpected
    -0.50
    httphttps
    -0.50
    Unexpected
    -0.49
     plötzlich
    -0.49
    +#+#
    -0.49
    POSITIVE LOGITS
     detrimental
    1.02
     damaging
    0.99
     harmful
    0.97
     destructive
    0.95
     doomed
    0.92
     disastrous
    0.90
     harm
    0.89
     damage
    0.87
     deleterious
    0.86
     detriment
    0.85
    Activations Density 0.506%

    No Known Activations