Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 11-GEMMASCOPE-RES-16K
    6. 5766
    Prev
    Next
    INDEX
    Explanations

    words related to 'able' forms, particularly focusing on various adaptations of the suffix "able"

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 11-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_11/width_16k/average_l0_80
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.11.hook_resid_post
    Hook Layer
    11
    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
    -0.84
    n
    -0.79
    es
    -0.74
    m
    -0.71
    <eos>
    -0.66
    9
    -0.65
     ***!
    -0.64
    InSection
    -0.64
     useEffect
    -0.63
    N
    -0.62
    POSITIVE LOGITS
    izable
    1.32
    vable
    1.22
     Theſe
    1.22
     Efq
    1.22
    urable
    1.17
    gable
    1.15
    ^(@)
    1.14
     ་་
    1.14
     myſelf
    1.14
     Jefus
    1.13
    Activations Density 0.238%

    No Known Activations