© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 2-GEMMASCOPE-RES-16K
    11. 4305
    Prev
    Next
    INDEX
    Explanations

    expressions of desire or intent related to preferences and actions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 2-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_2/width_16k/average_l0_67
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.hook_resid_post
    Hook Layer
    2
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    rungsseite
    -1.34
     Administrativna
    -1.23
    AnchorStyles
    -1.18
     invokingState
    -1.14
     autorytatywna
    -1.13
     Infórmanos
    -1.12
    webElementXpaths
    -1.10
    ロウィン
    -1.09
     HasFactory
    -1.09
    <pad>
    -1.08
    POSITIVE LOGITS
    ↵↵
    0.49
    ↵
    0.48
    1
    0.38
    <em>
    0.37
    2
    0.33
    </strong>
    0.33
    <strong>
    0.32
    <i>
    0.31
    7
    0.29
    </h1>
    0.29
    Activations Density 0.576%

    No Known Activations