© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    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. 8230
    Prev
    Next
    INDEX
    Explanations

    expressions and contexts related to enjoyment and fun

    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
    LabelTagHelper
    -0.90
     Normdatei
    -0.85
    IsMutable
    -0.85
     protoimpl
    -0.82
    ;">
    
    -0.79
    ardoor
    -0.78
     tartalomajánló
    -0.76
     propOrder
    -0.75
    ngdoc
    -0.74
     VIAF
    -0.74
    POSITIVE LOGITS
     fun
    1.63
     FUN
    1.60
    FUN
    1.48
     Fun
    1.45
    fun
    1.43
    Fun
    1.35
    funcs
    1.04
     functor
    0.98
     Spaß
    0.98
     functools
    0.94
    Activations Density 0.025%

    No Known Activations