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. 15-GEMMASCOPE-RES-16K
    6. 1863
    Prev
    Next
    INDEX
    Explanations

    terms related to symbolism and meaning in relationships

    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
     hại
    -0.54
     ويكيپيديا
    -0.51
     étr
    -0.51
     pretext
    -0.49
     Quincy
    -0.49
     weirdly
    -0.49
    ontale
    -0.49
     intéress
    -0.48
     stupidly
    -0.48
     nakalista
    -0.48
    POSITIVE LOGITS
     AssemblyVersion
    0.76
    zzleHttp
    0.73
     symbol
    0.59
     symbo
    0.55
     символ
    0.53
     authService
    0.53
     symbolizes
    0.52
     betweenstory
    0.52
    DrawerToggle
    0.51
    yargs
    0.51
    Activations Density 0.293%

    No Known Activations