© 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. 9537
    Prev
    Next
    INDEX
    Explanations

    concepts and discussions related to progress and achievement, particularly in financial contexts

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

    forward movement or advancement towards goals and objectives.

    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
    httphttps
    -0.73
     CreateTagHelper
    -0.61
     للمعارف
    -0.57
    /**
    -0.54
    Diweddarwch
    -0.53
     lenker
    -0.52
    ngdoc
    -0.51
    AndEndTag
    -0.49
    InstrumentedTest
    -0.49
    StoryboardSegue
    -0.47
    POSITIVE LOGITS
     progress
    3.20
    progress
    2.78
     Progress
    2.72
    Progress
    2.61
     PROGRESS
    2.48
     progreso
    2.33
    PROGRESS
    2.23
     progresso
    2.23
     progresses
    2.17
     progrès
    2.14
    Activations Density 0.456%

    No Known Activations