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-2-2B
    4. Residual Stream - 16k
    5. 0-GEMMASCOPE-RES-16K
    6. 7969
    Prev
    Next
    INDEX
    Explanations

    terms associated with aspirations and ambitions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 0-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_0/width_16k/average_l0_105
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.hook_resid_post
    Hook Layer
    0
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Gambas
    -0.76
     <=",
    -0.70
     CGRectMake
    -0.67
     NSCoder
    -0.67
    ramientas
    -0.66
    initWithFrame
    -0.66
     referrerpolicy
    -0.65
     HasFactory
    -0.65
     Shaksp
    -0.64
    PerformLayout
    -0.64
    POSITIVE LOGITS
     dreams
    0.78
     dream
    0.74
    dream
    0.65
     sign
    0.64
     Dreams
    0.63
     signed
    0.63
    Dream
    0.63
     Dream
    0.61
     Traum
    0.59
     Sign
    0.57
    Activations Density 0.129%

    No Known Activations