© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 1-GEMMASCOPE-RES-16K
    11. 2728
    Prev
    Next
    INDEX
    Explanations

    various forms of the word "statement," indicating a focus on assertions or declarations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 1-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_1/width_16k/average_l0_69
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.1.hook_resid_post
    Hook Layer
    1
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     CreateTagHelper
    -0.59
    こうして
    -0.50
    IVEREF
    -0.50
    évaluateur
    -0.49
    DockStyle
    -0.49
     obviamente
    -0.48
    enumi
    -0.44
    Jîn
    -0.44
    MockMvc
    -0.43
    RTHOOK
    -0.42
    POSITIVE LOGITS
     statement
    2.55
     statements
    2.33
     Statement
    2.19
    statement
    2.08
     STATEMENT
    2.05
     Statements
    2.05
    Statement
    1.95
    statements
    1.91
    Statements
    1.87
    STATEMENT
    1.80
    Activations Density 0.255%

    No Known Activations