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-2-9B-IT
    4. Residual Stream - 131k
    5. 9-GEMMASCOPE-RES-131K
    6. 128342
    Prev
    Next
    INDEX
    Explanations

    references to programming libraries or scripts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 9-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_9/width_131k/average_l0_121
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.9.hook_resid_post
    Hook Layer
    9
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    WebElementEntity
    -0.39
    nestjs
    -0.38
     createSlice
    -0.37
    iteritems
    -0.34
    exitRule
    -0.34
    RefNanny
    -0.34
    -------------</
    -0.33
    <bos>
    -0.33
    AndroidJUnit
    -0.32
     MonoBehaviour
    -0.32
    POSITIVE LOGITS
    OGND
    0.70
     незавершена
    0.69
    addPreferredGap
    0.58
    出版年
    0.56
     houſe
    0.54
     تضيفلها
    0.53
    FontOfSize
    0.53
     paño
    0.52
    tehende
    0.52
     informée
    0.51
    Activations Density 0.006%

    No Known Activations