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. 14-GEMMASCOPE-RES-16K
    6. 7389
    Prev
    Next
    INDEX
    Explanations

    action verbs and their frequencies in a narrative context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 14-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_14/width_16k/average_l0_84
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.14.hook_resid_post
    Hook Layer
    14
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Freund
    -0.45
     Baby
    -0.45
     self
    -0.39
     Part
    -0.39
     admitted
    -0.38
    spraak
    -0.38
     Self
    -0.37
    moveToFirst
    -0.37
    wały
    -0.37
     so
    -0.37
    POSITIVE LOGITS
    RegistryLite
    0.87
    mybatisplus
    0.85
     unplayable
    0.82
     tartalomajánló
    0.82
    ніципалі
    0.78
    __':
    
    0.75
     <=",
    0.73
     houſe
    0.72
    IUrlHelper
    0.71
    Lähteet
    0.71
    Activations Density 0.347%

    No Known Activations