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. 6-GEMMASCOPE-RES-16K
    6. 308
    Prev
    Next
    INDEX
    Explanations

    emotional expressions and sentiments related to relationships

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

    narrative writing or storytelling techniques, particularly tracking character thoughts and emotional inner monologues.

    oai_token-act-pair · claude-3-5-haiku-20241022Triggered by @neilrathi
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 6-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_6/width_16k/average_l0_70
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.6.hook_resid_post
    Hook Layer
    6
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    rasında
    -0.55
     teritor
    -0.50
     provide
    -0.50
    \
    -0.50
    Jahres
    -0.49
     themſelves
    -0.48
     automatically
    -0.48
     general
    -0.48
    伃
    -0.48
    auta
    -0.47
    POSITIVE LOGITS
    tagHelperRunner
    1.08
    ंदीखरीदारी
    0.90
    __':
    
    0.81
    MigrationBuilder
    0.78
    tagext
    0.75
    הערות
    0.75
    awtextra
    0.74
    IMPORTED
    0.69
    帖最后由
    0.68
    __":
    
    0.68
    Activations Density 0.229%

    No Known Activations