© 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
    4. Residual Stream - 16k
    5. 31-GEMMASCOPE-RES-16K
    6. 15958
    Prev
    Next
    INDEX
    Explanations

    directional terms related to geographical locations

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

    directional spatial references combined with distances or measurements.

    oai_token-act-pair · claude-4-5-haikuTriggered by @emiglarou
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 31-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_31/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.31.hook_resid_post
    Hook Layer
    31
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    AddTagHelper
    -0.71
    httphttps
    -0.68
    addCriterion
    -0.63
    IsContent
    -0.63
    TestingModule
    -0.60
     Normdatei
    -0.60
    parsedMessage
    -0.60
    OrBuilder
    -0.59
     oprot
    -0.58
     informée
    -0.57
    POSITIVE LOGITS
    สุด
    0.52
    wards
    0.47
     judiciales
    0.40
    most
    0.39
     past
    0.37
    ward
    0.36
     poches
    0.35
    ishly
    0.33
     praktis
    0.33
    Panamoan
    0.33
    Activations Density 0.209%

    No Known Activations