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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 24-GEMMASCOPE-RES-16K
    6. 4939
    Prev
    Next
    INDEX
    Explanations

    terms related to interactions and responses of individuals or entities to various influences or factors

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

    followed by adverbs

    np_acts-logits-general · gemini-2.0-flash

    manner of action or state

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 24-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_24/width_16k/average_l0_73
    Prompts (Dashboard)
    36,864 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
     vectorielles
    -1.06
     normaux
    -0.93
     récents
    -0.92
     quelcon
    -0.91
     automatiques
    -0.87
     rapides
    -0.87
     sociala
    -0.84
     positifs
    -0.83
     scolaires
    -0.82
     perfetto
    -0.81
    POSITIVE LOGITS
     secara
    0.79
     imagin
    0.65
     produ
    0.64
     expan
    0.63
     conten
    0.61
     gener
    0.61
     detec
    0.61
     addi
    0.60
     expres
    0.59
     permis
    0.59
    Activations Density 2.402%

    No Known Activations