© 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-IT
    4. Residual Stream - 131k
    5. 20-GEMMASCOPE-RES-131K
    6. 102216
    Prev
    Next
    INDEX
    Explanations

    instances of the term "back" in various contexts

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

    back followed by a description

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_131k/average_l0_81
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    دانشنامهٔ
    -0.60
     laſſen
    -0.57
    fjspx
    -0.57
    CppMethod
    -0.55
    jMenuItem
    -0.55
    NameInMap
    -0.52
     embodi
    -0.51
     defaultstate
    -0.49
     NgModule
    -0.49
     müſſen
    -0.49
    POSITIVE LOGITS
    Back
    1.18
     Back
    1.18
     back
    1.17
     BACK
    1.13
    back
    1.13
    BACK
    1.01
     backs
    0.83
     Backman
    0.80
    btnBack
    0.79
     バック
    0.74
    Activations Density 0.022%

    No Known Activations