Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit 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. 5-GEMMASCOPE-RES-16K
    6. 1717
    Prev
    Next
    INDEX
    Explanations

    references to guidelines and instructions

    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
    endmodule
    -0.58
     Pingback
    -0.57
     CanadaChoose
    -0.56
     resourceCulture
    -0.51
    principalColumn
    -0.48
    antd
    -0.48
    strncmp
    -0.48
    parsedMessage
    -0.48
    люс
    -0.48
    AnimationsModule
    -0.47
    POSITIVE LOGITS
     instructions
    1.32
    instructions
    1.16
     manuals
    1.13
     Instructions
    1.05
     Manuals
    1.02
     directions
    1.01
     instruction
    1.00
    Instructions
    0.96
     guides
    0.95
     INSTRUCTIONS
    0.92
    Activations Density 0.367%

    No Known Activations