© 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. 1233
    Prev
    Next
    INDEX
    Explanations

    chemical processes and procedures related to laboratory techniques

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

    Steps in a chemical or scientific procedure

    np_acts-logits-general · gemini-2.0-flash

    extraction and purification steps

    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
    randint
    -0.51
     personnalisés
    -0.48
    mut
    -0.48
     kny
    -0.47
     personnalisée
    -0.44
    Random
    -0.42
    Ply
    -0.41
     Dioxide
    -0.41
     Rus
    -0.40
     mémor
    -0.40
    POSITIVE LOGITS
    脚注の使い方
    0.89
    IsContent
    0.80
     separating
    0.74
    RectangleBorder
    0.72
     resourceCulture
    0.70
    ########.
    0.68
     recoverable
    0.67
    دانشنامهٔ
    0.67
    WillAppear
    0.67
     صوتيه
    0.66
    Activations Density 1.117%

    No Known Activations