© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 24-GEMMASCOPE-RES-16K
    6. 5725
    Prev
    Next
    INDEX
    Explanations

    texts that express formality and structure in communication

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

    associated with being cold or rigid

    np_acts-logits-general · gemini-2.0-flash

    austere, cold, sober, rigid qualities

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 24-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_24/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.24.hook_resid_post
    Hook Layer
    24
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     diverti
    -0.46
    輕鬆
    -0.44
    lusconi
    -0.43
     freely
    -0.43
     loosely
    -0.43
     рассла
    -0.42
    自由に
    -0.41
    BASEPATH
    -0.41
    柔らかい
    -0.40
     permis
    -0.40
    POSITIVE LOGITS
     austere
    0.79
     cold
    0.74
     frío
    0.68
     froide
    0.68
     froid
    0.68
     somber
    0.67
    twimg
    0.65
     soğ
    0.64
    cold
    0.64
     sober
    0.64
    Activations Density 0.856%

    No Known Activations