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. 8-GEMMASCOPE-RES-16K
    6. 5935
    Prev
    Next
    INDEX
    Explanations

    terms related to databases

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 8-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_8/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.8.hook_resid_post
    Hook Layer
    8
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    StructEnd
    -0.88
     Abp
    -0.81
    มาะ
    -0.74
    hoeddwyd
    -0.68
    omány
    -0.68
    izr
    -0.66
     myco
    -0.66
     gynhyrchwyd
    -0.64
    days
    -0.64
     eddy
    -0.63
    POSITIVE LOGITS
     ་་
    0.98
     raiſ
    0.95
     ―――――
    0.94
     Efq
    0.89
     Anſ
    0.89
     Reſ
    0.86
     pii
    0.86
     Löwen
    0.85
     databases
    0.85
     photolibrary
    0.84
    Activations Density 0.084%

    No Known Activations