© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 5-GEMMASCOPE-RES-16K
    11. 5160
    Prev
    Next
    INDEX
    Explanations

    instances of XML or HTML-like structure in code snippets

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.5.hook_resid_post
    Hook Layer
    5
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    oa̍t
    -0.92
    expandindo
    -0.80
     Италијани
    -0.79
    :✨
    -0.79
     &___
    -0.77
    ]=>
    -0.74
    }-*/;
    -0.70
    orexia
    -0.69
    transQ
    -0.69
    CIOS
    -0.69
    POSITIVE LOGITS
    ReusableCell
    0.58
    dzie
    0.47
     IndexPath
    0.44
    这条
    0.43
    providedIn
    0.42
     پرد
    0.42
    บัติ
    0.41
    <sub>
    0.41
     Dijo
    0.40
     diu
    0.40
    Activations Density 0.029%

    No Known Activations