© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 31-GEMMASCOPE-RES-16K
    11. 3541
    Prev
    Next
    INDEX
    Explanations

    key concepts related to measurement and evaluation of offers or proposals

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

    phrases expressing logical reasoning or explanation (words like "this," "way," "in," "that" in contexts of argumentation and conclusion-drawing).

    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
    NameInMap
    -0.51
     jsPsych
    -0.48
    ăzi
    -0.48
     Italijani
    -0.47
    ExtendWith
    -0.44
    $_['
    -0.42
     defaultstate
    -0.41
     devons
    -0.40
     îna
    -0.39
    MergeFrom
    -0.39
    POSITIVE LOGITS
     thus
    2.42
    Thus
    2.02
     Thus
    1.93
    thus
    1.92
     así
    1.88
     таким
    1.85
     ainsi
    1.70
    这样
    1.70
     näin
    1.66
    這樣
    1.63
    Activations Density 0.729%

    No Known Activations