© 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-2-9B-IT
    7. Residual Stream - 131k
    9. 20-GEMMASCOPE-RES-131K
    11. 8193
    Prev
    Next
    INDEX
    Explanations

    method calls related to handling data in intents

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_131k/average_l0_81
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    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
    userDao
    -0.42
    onMouse
    -0.41
    SpringBootTest
    -0.40
    HttpStatus
    -0.37
     []:
    -0.35
    可
    -0.35
    taskList
    -0.35
     Dienste
    -0.34
    ်း
    -0.33
    qDebug
    -0.33
    POSITIVE LOGITS
    getStringExtra
    2.59
    putExtra
    1.38
    getExtras
    1.05
    textra
    0.83
    StoryboardSegue
    0.74
    AddHtmlAttribute
    0.73
    featureID
    0.73
     getIntent
    0.73
     objectForKey
    0.71
     препратки
    0.71
    Activations Density 0.001%

    No Known Activations