© 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. 33-GEMMASCOPE-RES-16K
    6. 11799
    Prev
    Next
    INDEX
    Explanations

    phrases and keywords related to comparisons and differences in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 33-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_33/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.33.hook_resid_post
    Hook Layer
    33
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     الحره
    -0.36
    ptid
    -0.34
    الدراسه
    -0.34
    UESDAY
    -0.31
    TagNumber
    -0.28
     eins
    -0.28
    Cyfarwyddwr
    -0.28
     SYLLABLE
    -0.27
     inapropiados
    -0.27
    一来
    -0.27
    POSITIVE LOGITS
     difference
    3.78
     differences
    3.41
    difference
    3.36
     Difference
    3.33
    Difference
    3.27
     Differences
    3.17
    Differences
    3.11
     DIFFERENCE
    3.03
    differences
    3.03
     différence
    2.94
    Activations Density 2.000%

    No Known Activations