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. 19-GEMMASCOPE-RES-16K
    6. 2170
    Prev
    Next
    INDEX
    Explanations

    technical terminology and concepts related to memory management and threading in programming

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 19-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_19/width_16k/average_l0_73
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.19.hook_resid_post
    Hook Layer
    19
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    omycin
    -0.59
    posedge
    -0.50
    OrEqualTo
    -0.49
    fiets
    -0.47
     fac
    -0.47
    ocene
    -0.47
     Же
    -0.46
    Història
    -0.45
    urals
    -0.44
    TagHelpers
    -0.44
    POSITIVE LOGITS
     native
    0.96
     nativo
    0.92
    native
    0.90
     intptr
    0.88
     nativa
    0.86
     gynhyrchwyd
    0.86
    Native
    0.84
     Native
    0.82
    JNI
    0.79
     JNI
    0.79
    Activations Density 0.540%

    No Known Activations