© 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. 10-GEMMASCOPE-RES-16K
    11. 10556
    Prev
    Next
    INDEX
    Explanations

    words related to the concept of being able or capable of something

    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
    ing
    -0.87
    n
    -0.82
    m
    -0.74
    es
    -0.71
    <eos>
    -0.69
    9
    -0.68
    th
    -0.66
    2
    -0.65
    <h2>
    -0.63
    ↵↵
    -0.62
    POSITIVE LOGITS
    izable
    1.34
    vable
    1.25
    urable
    1.24
    ^(@)
    1.22
     Theſe
    1.20
    chable
    1.19
     Efq
    1.19
     myſelf
    1.18
    asable
    1.17
     Jefus
    1.14
    Activations Density 0.253%

    No Known Activations