© 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. 15340
    Prev
    Next
    INDEX
    Explanations

    terms related to specific functions and components in various mechanical or scientific contexts

    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
    +:+
    -0.87
    RectangleBorder
    -0.85
    脚注の使い方
    -0.75
     doInBackground
    -0.69
     незавершена
    -0.66
    Hozzáférés
    -0.66
    Hrsg
    -0.66
    accharides
    -0.64
     weten
    -0.64
    localPosition
    -0.63
    POSITIVE LOGITS
     ſta
    0.68
    σθαι
    0.64
     Reſ
    0.64
     Diſ
    0.63
     sandero
    0.63
     houſe
    0.63
     _:
    0.62
     pleaſure
    0.61
     ſche
    0.59
    ETY
    0.58
    Activations Density 1.935%

    No Known Activations