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. 4302
    Prev
    Next
    INDEX
    Explanations

    terms related to financial burdens and their impact on societal issues

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

    Reasons or explanations for something

    np_acts-logits-general · gemini-2.0-flash

    explains why

    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
     Majefty
    -0.65
     poffe
    -0.64
    wpi
    -0.62
    covia
    -0.61
     Efq
    -0.61
     Jefus
    -0.61
    GOTREF
    -0.59
    InSection
    -0.59
    MigrationBuilder
    -0.59
     Houſe
    -0.57
    POSITIVE LOGITS
     reason
    1.69
     why
    1.61
     reasons
    1.41
    reason
    1.33
    why
    1.25
     contributing
    1.23
    Reasons
    1.22
    Reason
    1.20
     Reasons
    1.19
    Why
    1.18
    Activations Density 0.528%

    No Known Activations