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

    Neuronpedia

    APIAssistant AxisNEWCircuit 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. 16-GEMMASCOPE-RES-16K
    6. 5147
    Prev
    Next
    INDEX
    Explanations

    gerunds and present participles that indicate ongoing actions or processes

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

    ending in "-ing"

    np_acts-logits-general · gemini-2.0-flash

    verbs describing actions or states

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 16-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_16/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.16.hook_resid_post
    Hook Layer
    16
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    bindet
    -0.70
    setopt
    -0.68
    gebob
    -0.62
    issauga
    -0.61
     getRule
    -0.61
    ftagPool
    -0.59
    ArgsConstructor
    -0.58
    UrlEncoded
    -0.57
     Parton
    -0.57
    cách
    -0.57
    POSITIVE LOGITS
    ting
    1.07
    ating
    0.99
    ging
    0.94
    GGGG
    0.92
    cting
    0.89
    gggg
    0.89
    ly
    0.89
    tons
    0.83
    lapsingToolbar
    0.82
    izing
    0.80
    Activations Density 0.719%

    No Known Activations