© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 33-GEMMASCOPE-RES-16K
    11. 8190
    Prev
    Next
    INDEX
    Explanations

    intensifiers or extreme adjectives that amplify the description of nouns or situations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 33-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_33/width_16k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.33.hook_resid_post
    Hook Layer
    33
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     autorytatywna
    -0.68
    ########.
    -0.61
    somewhat
    -0.59
     كومونز
    -0.58
    Personendaten
    -0.53
     ujednoznacz
    -0.52
    Somewhat
    -0.52
    出版年
    -0.52
     somewhat
    -0.52
    باردا
    -0.51
    POSITIVE LOGITS
     underrated
    0.47
     sekali
    0.45
     underestimated
    0.44
     ProtoMessage
    0.41
     cool
    0.40
     unfair
    0.40
     impressive
    0.39
     fucking
    0.39
     wrong
    0.38
     freaking
    0.38
    Activations Density 0.302%

    No Known Activations