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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 10-GEMMASCOPE-RES-16K
    6. 13177
    Prev
    Next
    INDEX
    Explanations

    names of people and references to their actions or statements

    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
    DockStyle
    -0.63
    μί
    -0.53
    esModule
    -0.51
    sizeCache
    -0.45
    jka
    -0.44
    reactstrap
    -0.44
     assoluto
    -0.44
     stesso
    -0.43
     kesempatan
    -0.42
    فر
    -0.42
    POSITIVE LOGITS
     Roskov
    1.18
     externi
    0.93
     незавершена
    0.85
     jadx
    0.83
    хьтан
    0.83
     оригіналу
    0.82
    AccessorTable
    0.79
     beginnetje
    0.76
     للاسماء
    0.74
     kaarangay
    0.69
    Activations Density 0.302%

    No Known Activations