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

    Neuronpedia

    APICircuit 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. 16-GEMMASCOPE-RES-16K
    6. 6311
    Prev
    Next
    INDEX
    Explanations

    information related to product availability and specifications

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Android devices and patents

    np_acts-logits-general · gemini-2.0-flash

    Android phones and tablets

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 16-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_16/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.16.hook_resid_post
    Hook Layer
    16
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ütfen
    -0.53
     BoxFit
    -0.51
    enggarakan
    -0.48
     discord
    -0.47
     OBITUARY
    -0.46
    ]")]
    -0.46
    discord
    -0.46
    thane
    -0.44
     twitch
    -0.44
     IFF
    -0.44
    POSITIVE LOGITS
     handset
    0.86
     Android
    0.82
     device
    0.77
     phones
    0.75
     devices
    0.74
     hardware
    0.74
     Samsung
    0.72
     Device
    0.72
     consumer
    0.69
     smartphones
    0.69
    Activations Density 0.395%

    No Known Activations