Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 16-GEMMASCOPE-RES-16K
    6. 4178
    Prev
    Next
    INDEX
    Explanations

    academic and research-related terminology and phrases, particularly in the context of collaborative efforts

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

    authors, institutions, and countries

    np_acts-logits-general · gemini-2.0-flash

    author, institution, country collaborations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 16-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_16/width_16k/average_l0_78
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.16.hook_resid_post
    Hook Layer
    16
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     reality
    -0.46
    iglesia
    -0.45
    valueOf
    -0.44
     store
    -0.41
    󠁢
    -0.41
     оригіналу
    -0.40
     motor
    -0.40
     Motor
    -0.39
     consum
    -0.39
    店
    -0.39
    POSITIVE LOGITS
     postdoctoral
    0.85
    ]--;
    0.77
     fellowships
    0.76
     betweenstory
    0.76
     faculty
    0.75
     colleague
    0.74
     collègues
    0.74
     colleagues
    0.72
     Scopus
    0.72
     Professors
    0.72
    Activations Density 0.977%

    No Known Activations