Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 27-GEMMASCOPE-RES-16K
    6. 9867
    Prev
    Next
    INDEX
    Explanations

    numeric representations and extracts numerical data

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 27-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_27/width_16k/average_l0_118
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.27.hook_resid_post
    Hook Layer
    27
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    LookAnd
    -0.47
    StructEnd
    -0.46
    utilisons
    -0.45
    writeField
    -0.43
    addCriterion
    -0.43
    PerformLayout
    -0.42
    RegressionTest
    -0.41
     متعلقه
    -0.40
     actionMode
    -0.40
    ronique
    -0.40
    POSITIVE LOGITS
    EditorGUILayout
    0.45
     years
    0.41
     AssemblyCompany
    0.40
    TestingModule
    0.39
     year
    0.39
    Viited
    0.39
    gridy
    0.39
    |};
    0.38
     gynhyrchwyd
    0.38
     roku
    0.37
    Activations Density 0.178%

    No Known Activations