© 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. 18-GEMMASCOPE-RES-16K
    11. 11231
    Prev
    Next
    INDEX
    Explanations

    numerical values and their associated patterns

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

    Numbers with decimals or in parentheses

    np_acts-logits-general · gemini-2.0-flash

    numbers and punctuation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.hook_resid_post
    Hook Layer
    18
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     itſelf
    -1.34
     ་་
    -1.29
     InputDecoration
    -1.21
     pleaſure
    -1.20
     betweenstory
    -1.19
     myſelf
    -1.16
    ſelf
    -1.15
     ſtate
    -1.14
    NUMX
    -1.14
     ſind
    -1.13
    POSITIVE LOGITS
     
    1.13
    1
    1.10
    0
    1.04
    2
    1.02
    5
    1.01
    4
    1.00
    3
    0.95
    8
    0.95
    7
    0.91
    6
    0.91
    Activations Density 2.984%

    No Known Activations