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-2-9B-IT
    4. Residual Stream - 16k
    5. 20-GEMMASCOPE-RES-16K
    6. 15160
    Prev
    Next
    INDEX
    Explanations

    references to spells and magical elements

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

    Followed by first name

    np_acts-logits-general · gemini-2.0-flash

    Kiki activation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_16k/average_l0_91
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    getSystemService
    -0.52
    extAlignment
    -0.49
    actéristi
    -0.48
    PDOException
    -0.44
    úblico
    -0.41
    LLocation
    -0.40
     acceptez
    -0.40
     spirituale
    -0.40
    AndEndTag
    -0.40
    GEBURTS
    -0.39
    POSITIVE LOGITS
    ंदीखरीदारी
    0.42
    scryfall
    0.40
    日閲覧
    0.40
     الرياضيه
    0.39
    astify
    0.38
    <()>
    0.37
     Lugano
    0.37
    Rel
    0.36
    Flush
    0.36
    ፩
    0.36
    Activations Density 0.076%

    No Known Activations