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. 3490
    Prev
    Next
    INDEX
    Explanations

    references to meetings and conferences

    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
    izoen
    -0.53
     /\.
    -0.53
    ivotopis
    -0.48
    龄
    -0.47
     infan
    -0.47
     Illuminate
    -0.46
    :^
    -0.46
     pulumi
    -0.46
    jsdelivr
    -0.45
    GenerationType
    -0.45
    POSITIVE LOGITS
     meetings
    1.66
     meeting
    1.58
     Meetings
    1.51
    Meetings
    1.48
     Meeting
    1.47
    meetings
    1.44
    meeting
    1.41
    Meeting
    1.41
     MEETING
    1.35
     reuniones
    1.14
    Activations Density 0.218%

    No Known Activations