Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B-IT
    4. Residual Stream - 131k
    5. 9-GEMMASCOPE-RES-131K
    6. 38560
    Prev
    Next
    INDEX
    Explanations

    phrases and references related to something being in or associated with the "back" of an object or location

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

    front and back locations

    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
     zatem
    -0.46
     către
    -0.46
     singkat
    -0.43
     voorbij
    -0.42
     دریافت‌شده
    -0.40
     lecz
    -0.40
     koszulka
    -0.40
     tunggal
    -0.40
    hingga
    -0.39
     feira
    -0.38
    POSITIVE LOGITS
     Front
    0.63
     rear
    0.61
    Front
    0.59
     Rear
    0.57
     front
    0.57
    Rear
    0.56
    Middle
    0.55
    rear
    0.55
     FRONT
    0.53
     intptr
    0.53
    Activations Density 0.010%

    No Known Activations