© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 34-GEMMASCOPE-RES-16K
    6. 11267
    Prev
    Next
    INDEX
    Explanations

    text related to academic and biographical details

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 34-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_34/width_16k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.34.hook_resid_post
    Hook Layer
    34
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Населення
    -0.45
     WebDriverWait
    -0.43
    WebControls
    -0.42
    calientes
    -0.38
    addContainerGap
    -0.37
     dangere
    -0.37
     kaarangay
    -0.35
    嚷
    -0.35
    abestanden
    -0.35
     errno
    -0.35
    POSITIVE LOGITS
     bio
    2.28
     biography
    2.19
     biographical
    2.00
    bio
    1.93
     Bio
    1.89
     Biography
    1.88
     biographies
    1.88
     био
    1.79
    Bio
    1.76
    biography
    1.76
    Activations Density 0.354%

    No Known Activations