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. 13-GEMMASCOPE-RES-16K
    6. 12723
    Prev
    Next
    INDEX
    Explanations

    phrases related to fear and control tactics in a societal context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 13-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_13/width_16k/average_l0_84
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.13.hook_resid_post
    Hook Layer
    13
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     zvuky
    -0.52
     roze
    -0.44
    ########.
    -0.42
     Pflicht
    -0.41
    TAIN
    -0.40
     tốc
    -0.39
     consommation
    -0.38
    '];?>
    -0.38
     fæ
    -0.38
     recherche
    -0.38
    POSITIVE LOGITS
     deterrent
    0.76
     coercive
    0.75
     coercion
    0.70
     deterrence
    0.70
     dissu
    0.66
     scare
    0.66
    TypedDataSet
    0.66
     deterred
    0.66
     relâche
    0.64
     intimidation
    0.64
    Activations Density 0.304%

    No Known Activations