© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 10-GEMMASCOPE-RES-16K
    6. 12745
    Prev
    Next
    INDEX
    Explanations

    words or terms related to procedures, processes, or treatments

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 10-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_10/width_16k/average_l0_77
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.10.hook_resid_post
    Hook Layer
    10
    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
    -1.02
     Audiodateien
    -0.93
     charset
    -0.88
     Magnetism
    -0.88
     Sando
    -0.86
     Montagu
    -0.83
     Eich
    -0.82
     Fet
    -0.82
    ]_{
    -0.81
     Zit
    -0.80
    POSITIVE LOGITS
    Pro
    1.49
     PRO
    1.42
     Pro
    1.40
    PRO
    1.29
    pro
    1.21
     pro
    1.05
     Pros
    1.01
    プロ
    1.00
     Prow
    0.96
     Prodi
    0.95
    Activations Density 0.211%

    No Known Activations