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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlogSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B-IT
    4. Residual Stream - 16k
    5. 9-GEMMASCOPE-RES-16K
    6. 6661
    Prev
    Next
    INDEX
    Explanations

    expressions of affection and endearment towards objects or beings

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 9-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-it-res/layer_9/width_16k/average_l0_88
    Prompts (Dashboard)
    24,576 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
    BufferException
    -0.56
     Substance
    -0.42
    ODB
    -0.40
    TestBed
    -0.40
    minecraftforge
    -0.39
    BoxShadow
    -0.38
    Itoa
    -0.36
    Solución
    -0.36
    ActivityCompat
    -0.36
     golpe
    -0.35
    POSITIVE LOGITS
     cute
    1.78
    Cute
    1.62
     adorable
    1.58
     Cute
    1.53
    cute
    1.46
     cutest
    1.40
    Adorable
    1.38
     Adorable
    1.36
     CUTE
    1.33
    adorable
    1.18
    Activations Density 0.185%

    No Known Activations