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-2-9B
    4. Residual Stream - 16k
    5. 24-GEMMASCOPE-RES-16K
    6. 969
    Prev
    Next
    INDEX
    Explanations

    concepts related to authority and submission to divine will

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

    after prepositions or conjunctions

    np_acts-logits-general · gemini-2.0-flash

    earthly and human concerns

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 24-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_24/width_16k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.hook_resid_post
    Hook Layer
    24
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     GenerationType
    -0.60
     allAfrica
    -0.56
    Panamoan
    -0.50
    itsubishi
    -0.49
    ✨:
    -0.48
     referenties
    -0.48
    adaptiveStyles
    -0.48
    хьтан
    -0.47
    ❋
    -0.47
    extreme
    -0.47
    POSITIVE LOGITS
     earthly
    0.52
     humanas
    0.41
     human
    0.37
     humaine
    0.35
     mortal
    0.35
     worldly
    0.35
     nargin
    0.35
    坞
    0.35
     getVersion
    0.34
     umane
    0.33
    Activations Density 0.191%

    No Known Activations