© 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. 9673
    Prev
    Next
    INDEX
    Explanations

    sequences of characters and potential code or data structures

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

    Seemingly random alphanumeric strings

    np_acts-logits-general · gemini-2.0-flash

    URLs and identifiers

    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
    Portale
    -1.01
    XmlAccessorType
    -1.00
    AxisAlignment
    -0.93
    بوابة
    -0.91
     BoxDecoration
    -0.86
    mybatisplus
    -0.82
    styleType
    -0.81
     незавершена
    -0.79
     مشين
    -0.76
    ✭✭
    -0.76
    POSITIVE LOGITS
    q
    0.73
    R
    0.71
    Z
    0.66
    2
    0.64
    B
    0.64
    M
    0.64
    X
    0.63
    3
    0.62
    k
    0.61
    4
    0.61
    Activations Density 0.077%

    No Known Activations