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
    4. Residual Stream - 16k
    5. 27-GEMMASCOPE-RES-16K
    6. 9706
    Prev
    Next
    INDEX
    Explanations

    references to various groups or classifications in 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
    électricité
    -0.52
    AndEndTag
    -0.50
     iNdEx
    -0.50
    "]));
    -0.48
     ioutil
    -0.47
     electricidad
    -0.46
     NavController
    -0.45
    harapkan
    -0.43
     îna
    -0.43
    SEVERE
    -0.43
    POSITIVE LOGITS
     group
    1.06
     Group
    1.05
    Group
    0.98
     GROUP
    0.98
     getGroup
    0.96
    group
    0.94
     groups
    0.86
    GROUP
    0.86
    roup
    0.85
    getGroup
    0.81
    Activations Density 0.184%

    No Known Activations