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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B-IT
    7. Residual Stream - 131k
    9. 9-GEMMASCOPE-RES-131K
    11. 81796
    Prev
    Next
    INDEX
    Explanations

    words and terms related to "ter" as a suffix, indicating a variety of concepts including roles, actions, or characters

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    er in names

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 9-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_9/width_131k/average_l0_121
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.9.hook_resid_post
    Hook Layer
    9
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    StoryboardSegue
    -0.61
     combineReducers
    -0.60
    دانشنامهٔ
    -0.60
    
    -0.59
    ніципалі
    -0.57
     Vikipedi
    -0.56
    horabuena
    -0.56
     Fais
    -0.56
     muualla
    -0.56
    ſelf
    -0.54
    POSITIVE LOGITS
    ter
    2.55
    TER
    1.86
    ters
    1.68
    Ter
    1.52
     ter
    1.50
     Ter
    1.38
     TER
    1.23
    tered
    1.16
    tere
    1.13
    tera
    1.08
    Activations Density 0.014%

    No Known Activations