© 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. 15-GEMMASCOPE-RES-16K
    6. 8823
    Prev
    Next
    INDEX
    Explanations

    words related to the concept of "ability" or potential, often in the context of qualities or features

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 15-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_15/width_16k/average_l0_78
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.15.hook_resid_post
    Hook Layer
    15
    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
    -0.93
    n
    -0.90
    es
    -0.79
    m
    -0.78
    N
    -0.69
    T
    -0.68
    2
    -0.67
    en
    -0.65
    X
    -0.64
    jspx
    -0.63
    POSITIVE LOGITS
    izable
    1.21
     Theſe
    1.20
     Efq
    1.17
    ABLE
    1.13
     myſelf
    1.13
    vable
    1.11
    neſs
    1.11
    ^(@)
    1.10
    ourable
    1.08
     Touchable
    1.08
    Activations Density 0.246%

    No Known Activations