© 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. 37-GEMMASCOPE-RES-16K
    6. 4880
    Prev
    Next
    INDEX
    Explanations

    various forms of the verb "to be" and expressions indicating time and context in scientific writing

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 37-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_37/width_16k/average_l0_124
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.37.hook_resid_post
    Hook Layer
    37
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    enumi
    -0.50
    exitRule
    -0.49
    enumii
    -0.48
    tagHelperRunner
    -0.45
    /**
    -0.43
    RegressionTest
    -0.43
    __':
    
    -0.39
    endfor
    -0.37
    yntaxException
    -0.37
    あれば
    -0.37
    POSITIVE LOGITS
     first
    3.97
    first
    3.25
     primeiro
    2.75
     eerste
    2.70
     primeira
    2.67
     primero
    2.66
     ersten
    2.61
     firft
    2.58
     FIRST
    2.53
     pertama
    2.53
    Activations Density 3.729%

    No Known Activations