© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 34-GEMMASCOPE-RES-16K
    11. 11538
    Prev
    Next
    INDEX
    Explanations

    occurrences of the word "hi" and its variations in different contexts

    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
    MessageTagHelper
    -0.51
    hObject
    -0.45
    exitRule
    -0.44
    ⓧ
    -0.43
    Ann
    -0.41
    CopyWith
    -0.41
    XtraReports
    -0.41
     CWE
    -0.40
    halb
    -0.40
    patra
    -0.39
    POSITIVE LOGITS
     Hi
    0.51
    Хи
    0.45
    Portály
    0.44
     hip
    0.41
    存于互联网档案馆
    0.41
     Hip
    0.41
    Hi
    0.40
    hihi
    0.40
     hi
    0.39
     hipo
    0.39
    Activations Density 0.137%

    No Known Activations