© 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. 3-GEMMASCOPE-RES-16K
    11. 5896
    Prev
    Next
    INDEX
    Explanations

    numerical values, particularly in a scientific context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 3-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_3/width_16k/average_l0_59
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.hook_resid_post
    Hook Layer
    3
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     للمعارف
    -0.88
    =============
    -0.86
    ]='\
    -0.85
     Bonneville
    -0.81
    mybatisplus
    -0.80
    دانشنامهٔ
    -0.79
     ffilm
    -0.79
    noinspection
    -0.75
    '],
    -0.75
    FAK
    -0.75
    POSITIVE LOGITS
    2
    1.74
    3
    1.13
    4
    1.04
    6
    0.95
    1
    0.94
    8
    0.94
    5
    0.91
    7
    0.91
    nd
    0.86
    iyle
    0.81
    Activations Density 0.633%

    No Known Activations