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. 192
    Prev
    Next
    INDEX
    Explanations

    terms related to policies, guidelines, and documentation

    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
    RTEE
    -0.54
    FXMLLoader
    -0.47
    ppelin
    -0.45
     te
    -0.44
    rän
    -0.43
     nasel
    -0.43
     Bacteriol
    -0.43
     مقاط
    -0.42
    mense
    -0.41
    ClientSize
    -0.41
    POSITIVE LOGITS
     policy
    0.86
     guidelines
    0.77
     Policy
    0.77
    policy
    0.76
     Guidelines
    0.71
     policies
    0.71
    guidelines
    0.70
     POLICY
    0.69
    Policy
    0.69
     objectives
    0.69
    Activations Density 0.330%

    No Known Activations