© 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. 16-GEMMASCOPE-RES-16K
    11. 1244
    Prev
    Next
    INDEX
    Explanations

    words and phrases related to conditions or situations that involve a context of "being" or "existence."

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

    French text with common prepositions

    np_acts-logits-general · gemini-2.0-flash

    french prepositions followed by phrases

    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
     HasFactory
    -0.68
    脚注の使い方
    -0.64
    ayuno
    -0.64
     récents
    -0.63
    новь
    -0.63
     sánchez
    -0.63
     picioare
    -0.63
    jména
    -0.61
     rodríguez
    -0.61
     pleaſure
    -0.60
    POSITIVE LOGITS
    +#+
    0.79
    ]-->
    0.58
    verwijspagina
    0.57
     forKey
    0.53
    intre
    0.51
     дописавши
    0.50
    entierung
    0.49
    BufferException
    0.49
    )':
    0.49
     Panchayat
    0.49
    Activations Density 0.050%

    No Known Activations