© 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. 3549
    Prev
    Next
    INDEX
    Explanations

    formal language related to comparisons and evaluations

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

    four-digit years (numbers in the format 19XX or 20XX).

    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
    hoeddwyd
    -0.47
    Personendaten
    -0.42
    ExecuteReader
    -0.41
    Tē
    -0.37
    Abitanti
    -0.36
     precis
    -0.35
     Precis
    -0.35
    knecht
    -0.34
     Accurate
    -0.33
    ConverterFactory
    -0.33
    POSITIVE LOGITS
     rival
    1.58
     comparable
    1.49
    comparable
    1.34
     rivals
    1.28
     compete
    1.27
     competes
    1.25
     competing
    1.22
     equal
    1.21
     Comparable
    1.21
     competitor
    1.17
    Activations Density 0.425%

    No Known Activations