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. 5-GEMMASCOPE-RES-16K
    6. 10821
    Prev
    Next
    INDEX
    Explanations

    terms and phrases related to fading, disappearance, and the effects of time on conditions or states

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.5.hook_resid_post
    Hook Layer
    5
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Wiktionnaire
    -0.75
     [*]
    -0.65
     (++
    -0.63
    opre
    -0.60
    clientX
    -0.58
    opc
    -0.58
    maki
    -0.58
     plena
    -0.58
    ,‎
    -0.57
     Loved
    -0.57
    POSITIVE LOGITS
     fade
    1.26
     fading
    1.19
     fades
    1.19
     faded
    1.08
     disappear
    1.02
     Fade
    0.98
    Fade
    0.96
     disappearing
    0.95
     vanish
    0.94
     vanishes
    0.94
    Activations Density 0.299%

    No Known Activations