© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 2-GEMMASCOPE-RES-16K
    11. 12639
    Prev
    Next
    INDEX
    Explanations

    the occurrence of the term "Ind" and its variations, indicating a focus on that specific lexical item

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 2-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_2/width_16k/average_l0_67
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.hook_resid_post
    Hook Layer
    2
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Morfologia
    -0.41
     løpet
    -0.39
     manguera
    -0.37
    étoit
    -0.36
     Ablauf
    -0.36
    ctivos
    -0.36
     preescolar
    -0.35
    enswert
    -0.35
    meria
    -0.35
     régionales
    -0.35
    POSITIVE LOGITS
     Ind
    3.77
    Ind
    3.52
     ind
    3.16
     IND
    3.11
    ind
    3.03
    IND
    2.81
     indi
    2.33
    indi
    2.19
    inde
    1.90
     Indi
    1.89
    Activations Density 0.269%

    No Known Activations