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-2-2B
    4. Residual Stream - 16k
    5. 23-GEMMASCOPE-RES-16K
    6. 8954
    Prev
    Next
    INDEX
    Explanations

    requests and responses from fans regarding their concerns and interactions with celebrities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 23-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_23/width_16k/average_l0_75
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.23.hook_resid_post
    Hook Layer
    23
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     noDo
    -0.75
    verifyException
    -0.74
    DebuggerNonUser
    -0.65
    ंदीखरीदारी
    -0.59
    topatho
    -0.58
    IntoConstraints
    -0.57
    CodeAttribute
    -0.57
    DialogContent
    -0.56
    chables
    -0.55
    ItemLayout
    -0.53
    POSITIVE LOGITS
     fan
    2.96
     fans
    2.88
    fans
    2.38
     Fans
    2.36
    fan
    2.32
    Fans
    2.29
     Fan
    2.21
    Fan
    2.16
     fanbase
    1.96
     fãs
    1.96
    Activations Density 0.265%

    No Known Activations