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. 6869
    Prev
    Next
    INDEX
    Explanations

    questions and inquiry phrases

    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
    ioutil
    -0.57
    caj
    -0.57
    brainly
    -0.56
    anneer
    -0.55
     UIView
    -0.55
    Essen
    -0.55
    בות
    -0.54
     المعيارى
    -0.54
    Enlaces
    -0.54
     ami
    -0.54
    POSITIVE LOGITS
     dumne
    0.66
     quelcon
    0.65
     civiles
    0.65
    CGRectMake
    0.60
     kasarigan
    0.59
     îna
    0.59
     combien
    0.57
    hyrchwyd
    0.56
     ljudi
    0.56
     laikā
    0.56
    Activations Density 0.078%

    No Known Activations