© 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-2-2B
    7. Residual Stream - 16k
    9. 4-GEMMASCOPE-RES-16K
    11. 15712
    Prev
    Next
    INDEX
    Explanations

    references to absolute values in mathematical expressions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 4-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_4/width_16k/average_l0_124
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.hook_resid_post
    Hook Layer
    4
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    LayoutStyle
    -0.84
    
    -0.69
     BoxFit
    -0.69
    extAlignment
    -0.68
    ]")]
    -0.66
    ležit
    -0.66
    afficheront
    -0.64
    LookAnd
    -0.62
    ждую
    -0.62
    windowFixed
    -0.62
    POSITIVE LOGITS
    abs
    1.86
     abs
    1.79
     Abs
    1.45
    Abs
    1.40
     ABS
    1.31
    ABS
    1.27
     absentee
    0.94
     ldc
    0.67
     abscess
    0.65
     fabs
    0.64
    Activations Density 0.071%

    No Known Activations