© 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. 15-GEMMASCOPE-RES-16K
    6. 13561
    Prev
    Next
    INDEX
    Explanations

    references to conditions or requirements for a process

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 15-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_15/width_16k/average_l0_78
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.15.hook_resid_post
    Hook Layer
    15
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    almost
    -0.54
     getApplication
    -0.50
    ████
    -0.50
    detectChanges
    -0.50
     useStyles
    -0.49
     almost
    -0.49
    Configurer
    -0.48
     nesten
    -0.47
     UITableViewCell
    -0.47
    MeasureSpec
    -0.46
    POSITIVE LOGITS
     preferably
    0.85
     Preferably
    0.84
    preferably
    0.76
     möglichst
    0.71
     enough
    0.67
    ContentAsync
    0.64
    能夠
    0.62
    StoreMessageInfo
    0.62
     بتوان
    0.61
     able
    0.61
    Activations Density 0.406%

    No Known Activations