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. 6-GEMMASCOPE-RES-16K
    6. 6337
    Prev
    Next
    INDEX
    Explanations

    contact information, particularly phone numbers and other means to reach out for assistance

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 6-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_6/width_16k/average_l0_70
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.6.hook_resid_post
    Hook Layer
    6
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     propOrder
    -0.96
     صوتيه
    -0.82
     AssemblyVersion
    -0.79
    oprot
    -0.77
    SharedDtor
    -0.76
    )?;
    -0.76
     mergeFrom
    -0.74
     setDescription
    -0.73
     <=",
    -0.72
    ValueStyle
    -0.71
    POSITIVE LOGITS
     Bre
    0.51
    ьа
    0.49
    væ
    0.46
    forName
    0.46
    6
    0.44
    ництво
    0.44
     telepon
    0.44
     $
    0.43
     gezond
    0.43
    quences
    0.43
    Activations Density 0.058%

    No Known Activations