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

    Neuronpedia

    APIAssistant AxisNEWCircuit 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. 9-GEMMASCOPE-RES-16K
    6. 15330
    Prev
    Next
    INDEX
    Explanations

    references to difficulties and complexities in marriage and relationships

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 9-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_9/width_16k/average_l0_73
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.9.hook_resid_post
    Hook Layer
    9
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    vanta
    -0.48
    碑
    -0.44
     Reuse
    -0.43
    ించ
    -0.41
    asily
    -0.40
    </tfoot>
    -0.40
    inerja
    -0.40
     provisoire
    -0.39
    tuber
    -0.39
     infancia
    -0.39
    POSITIVE LOGITS
     marital
    0.83
     spousal
    0.82
    StructEnd
    0.81
    Geplaatst
    0.79
     marriage
    0.76
    CloseOperation
    0.75
     husband
    0.74
     Marital
    0.74
    LookAnd
    0.73
     BoxFit
    0.73
    Activations Density 0.252%

    No Known Activations