© 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. 15-GEMMASCOPE-RES-16K
    11. 1930
    Prev
    Next
    INDEX
    Explanations

    phrases related to the process of applying for legal documents and permits

    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
     pinulongan
    -0.82
     مرئيه
    -0.73
     lenker
    -0.64
     ujednoznacz
    -0.62
    Clik
    -0.62
     <=",
    -0.61
    دانشنامهٔ
    -0.55
     gynhyrchwyd
    -0.55
     Sedangkan
    -0.55
    󠁴
    -0.54
    POSITIVE LOGITS
    <bos>
    0.69
    )";
    0.67
    InjectMocks
    0.63
    tvguidetime
    0.62
     aikaa
    0.61
    nocześnie
    0.59
    ίζει
    0.59
    ytick
    0.59
     رسد
    0.58
    RoutingModule
    0.58
    Activations Density 0.264%

    No Known Activations