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. 18-GEMMASCOPE-RES-16K
    6. 4029
    Prev
    Next
    INDEX
    Explanations

    symbols and formatting marks associated with data structures or references

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Code, file paths, or program instructions

    np_acts-logits-general · gemini-2.0-flash

    driving cars

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.hook_resid_post
    Hook Layer
    18
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Monfieur
    -0.96
     itſelf
    -0.94
     leaſt
    -0.91
     ſeveral
    -0.87
     Houſe
    -0.87
     diſt
    -0.85
     leſs
    -0.85
     raiſ
    -0.83
     Theſe
    -0.83
    aimana
    -0.83
    POSITIVE LOGITS
    </em>
    0.88
    </i>
    0.79
    /*
    0.74
    <em>
    0.70
    <i>
    0.65
    flex
    0.62
     Casper
    0.60
    r
    0.58
     NLR
    0.56
    MessageTagHelper
    0.56
    Activations Density 0.164%

    No Known Activations