© 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-2-2B
    7. Residual Stream - 16k
    9. 22-GEMMASCOPE-RES-16K
    11. 12728
    Prev
    Next
    INDEX
    Explanations

    phrases indicating qualities or assessments of nouns, especially related to being or existence

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

    Adjectives describing quality or condition

    np_acts-logits-general · gemini-2.0-flash

    evaluative states

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 22-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_22/width_16k/average_l0_72
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.hook_resid_post
    Hook Layer
    22
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    AndEndTag
    -0.85
    Autoritní
    -0.68
     externi
    -0.67
    RTDA
    -0.53
    timeScale
    -0.53
    StructEnd
    -0.50
    تقاوى
    -0.49
    principalTable
    -0.49
     betweenstory
    -0.49
    Сюжет
    -0.49
    POSITIVE LOGITS
     worth
    0.65
     problematic
    0.63
     winners
    0.62
     winner
    0.62
     touché
    0.60
    winners
    0.59
     tops
    0.58
     noteworthy
    0.58
    ouchable
    0.57
    +#+
    0.57
    Activations Density 0.344%

    No Known Activations